< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 17 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.0286. Min Range: -3.0286

Max Act: 3.0286. Min Act: -0.1700

Data Index: 4462799 (Open Web Text)

Max Activating Token Index: 277

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.9654. Min Act: -0.1700

Data Index: 876926 (Open Web Text)

Max Activating Token Index: 59

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.9495. Min Act: -0.1700

Data Index: 4375868 (Open Web Text)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.9495. Min Act: -0.1700

Data Index: 5137082 (Open Web Text)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.9179. Min Act: -0.1700

Data Index: 7996152 (Open Web Text)

Max Activating Token Index: 463

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.9020. Min Act: -0.1700

Data Index: 2876992 (Open Web Text)

Max Activating Token Index: 698

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.9179. Min Act: -0.1700

Data Index: 3908129 (Open Web Text)

Max Activating Token Index: 460

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.9020. Min Act: -0.1700

Data Index: 7815320 (Open Web Text)

Max Activating Token Index: 77

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.8861. Min Act: -0.1700

Data Index: 8611388 (Open Web Text)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.8861. Min Act: -0.1700

Data Index: 1574973 (Open Web Text)

Max Activating Token Index: 57

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.9020. Min Act: -0.1700

Data Index: 3413650 (Open Web Text)

Max Activating Token Index: 753

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.9020. Min Act: -0.1700

Data Index: 2874088 (Open Web Text)

Max Activating Token Index: 532

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.9179. Min Act: -0.1700

Data Index: 836163 (Open Web Text)

Max Activating Token Index: 846

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.9020. Min Act: -0.1700

Data Index: 4530173 (Open Web Text)

Max Activating Token Index: 507

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.8861. Min Act: -0.1700

Data Index: 3026256 (Open Web Text)

Max Activating Token Index: 66

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.8703. Min Act: -0.1700

Data Index: 7360789 (Open Web Text)

Max Activating Token Index: 122

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.8703. Min Act: -0.1700

Data Index: 4485322 (Open Web Text)

Max Activating Token Index: 61

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.8703. Min Act: -0.1700

Data Index: 6519537 (Open Web Text)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.8703. Min Act: -0.1700

Data Index: 2332457 (Open Web Text)

Max Activating Token Index: 664

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.0286. Min Range: -3.0286

Max Act: 2.8544. Min Act: -0.1700

Data Index: 7640439 (Open Web Text)

Max Activating Token Index: 141

Click toggle to see full text

Truncated

Full Text #19