Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 963 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.4356. Min Act: -0.1700

Data Index: 6017510 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.4255. Min Act: -0.1700

Data Index: 8350466 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.4146. Min Act: -0.1700

Data Index: 8536773 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.4166. Min Act: -0.1700

Data Index: 985062 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.4180. Min Act: -0.1700

Data Index: 5997626 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.4450. Min Act: -0.1700

Data Index: 5925778 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.4195. Min Act: -0.1700

Data Index: 2740021 (Open Web Text)

Max Activating Token Index: 455

Text #7

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.3902. Min Act: -0.1700

Data Index: 8201831 (Open Web Text)

Max Activating Token Index: 54

Text #8

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.3867. Min Act: -0.1700

Data Index: 5308699 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.3846. Min Act: -0.1700

Data Index: 4904500 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.3909. Min Act: -0.1700

Data Index: 7899716 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.3811. Min Act: -0.1700

Data Index: 5167634 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.3603. Min Act: -0.1700

Data Index: 5068543 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.3538. Min Act: -0.1700

Data Index: 2358736 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.3557. Min Act: -0.1700

Data Index: 3101957 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.3766. Min Act: -0.1700

Data Index: 1833720 (Open Web Text)

Max Activating Token Index: 73

Text #16

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.3519. Min Act: -0.1700

Data Index: 7221892 (Open Web Text)

Max Activating Token Index: 53

Text #17

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.3801. Min Act: -0.1700

Data Index: 7607579 (Open Web Text)

Max Activating Token Index: 639

Text #18

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.3770. Min Act: -0.1700

Data Index: 7670025 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.3696. Min Act: -0.1700

Data Index: 2119323 (Open Web Text)

Max Activating Token Index: 494