< Prev | Home | Model | Random | Next >

Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 23 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')



Text #0

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.7162. Min Act: -0.1700

Data Index: 3981673 (Open Web Text)

Max Activating Token Index: 254

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.5600. Min Act: -0.1700

Data Index: 4619315 (Open Web Text)

Max Activating Token Index: 521

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.4975. Min Act: -0.1700

Data Index: 4470784 (Open Web Text)

Max Activating Token Index: 739

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.3412. Min Act: -0.1700

Data Index: 6471637 (Open Web Text)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.3100. Min Act: -0.1700

Data Index: 6549201 (Open Web Text)

Max Activating Token Index: 38

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.2787. Min Act: -0.1700

Data Index: 3945810 (Open Web Text)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.3100. Min Act: -0.1700

Data Index: 2706219 (Open Web Text)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.1850. Min Act: -0.1700

Data Index: 7290173 (Open Web Text)

Max Activating Token Index: 982

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.2787. Min Act: -0.1700

Data Index: 1417072 (Open Web Text)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.2475. Min Act: -0.1700

Data Index: 4984097 (Open Web Text)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.2162. Min Act: -0.1700

Data Index: 5244912 (Open Web Text)

Max Activating Token Index: 247

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.2162. Min Act: -0.1700

Data Index: 7437101 (Open Web Text)

Max Activating Token Index: 986

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.2475. Min Act: -0.1700

Data Index: 4125938 (Open Web Text)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.1850. Min Act: -0.1700

Data Index: 3682680 (Open Web Text)

Max Activating Token Index: 206

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.1850. Min Act: -0.1700

Data Index: 5956692 (Open Web Text)

Max Activating Token Index: 829

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.2162. Min Act: -0.1700

Data Index: 2645431 (Open Web Text)

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.1537. Min Act: -0.1700

Data Index: 292503 (Open Web Text)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.2162. Min Act: -0.1700

Data Index: 3092347 (Open Web Text)

Max Activating Token Index: 899

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.2162. Min Act: -0.1700

Data Index: 3477230 (Open Web Text)

Max Activating Token Index: 407

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.1537. Min Act: -0.1700

Data Index: 4518392 (Open Web Text)

Max Activating Token Index: 964

Click toggle to see full text

Truncated

Full Text #19