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

Dataset: Open Web Text

Neuron 1182 in Layer 4

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: 5.4022. Min Range: -5.4022

Max Act: 5.3774. Min Act: -0.1700

Data Index: 1470248 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.4022. Min Range: -5.4022

Max Act: 5.3774. Min Act: -0.1700

Data Index: 2536664 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.4022. Min Range: -5.4022

Max Act: 5.3774. Min Act: -0.1700

Data Index: 4606065 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.4022. Min Range: -5.4022

Max Act: 5.4022. Min Act: -0.1700

Data Index: 6147502 (Open Web Text)

Max Activating Token Index: 981

Text #4

Max Range: 5.4022. Min Range: -5.4022

Max Act: 5.2828. Min Act: -0.1700

Data Index: 4140405 (Open Web Text)

Max Activating Token Index: 1018

Text #5

Max Range: 5.4022. Min Range: -5.4022

Max Act: 5.3316. Min Act: -0.1700

Data Index: 1215381 (Open Web Text)

Max Activating Token Index: 899

Text #6

Max Range: 5.4022. Min Range: -5.4022

Max Act: 5.2889. Min Act: -0.1700

Data Index: 2921015 (Open Web Text)

Max Activating Token Index: 994

Text #7

Max Range: 5.4022. Min Range: -5.4022

Max Act: 5.2428. Min Act: -0.1700

Data Index: 7067344 (Open Web Text)

Max Activating Token Index: 342

Text #8

Max Range: 5.4022. Min Range: -5.4022

Max Act: 5.2873. Min Act: -0.1700

Data Index: 8574163 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 5.4022. Min Range: -5.4022

Max Act: 5.3136. Min Act: -0.1700

Data Index: 7359183 (Open Web Text)

Max Activating Token Index: 221

Text #10

Max Range: 5.4022. Min Range: -5.4022

Max Act: 5.2700. Min Act: -0.1700

Data Index: 5958808 (Open Web Text)

Max Activating Token Index: 615

Text #11

Max Range: 5.4022. Min Range: -5.4022

Max Act: 5.2495. Min Act: -0.1700

Data Index: 2313471 (Open Web Text)

Max Activating Token Index: 835

Text #12

Max Range: 5.4022. Min Range: -5.4022

Max Act: 5.2431. Min Act: -0.1700

Data Index: 904561 (Open Web Text)

Max Activating Token Index: 519

Text #13

Max Range: 5.4022. Min Range: -5.4022

Max Act: 5.2443. Min Act: -0.1700

Data Index: 3412410 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.4022. Min Range: -5.4022

Max Act: 5.2566. Min Act: -0.1700

Data Index: 6423507 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 5.4022. Min Range: -5.4022

Max Act: 5.2199. Min Act: -0.1700

Data Index: 4217318 (Open Web Text)

Max Activating Token Index: 446

Text #16

Max Range: 5.4022. Min Range: -5.4022

Max Act: 5.1763. Min Act: -0.1700

Data Index: 6062367 (Open Web Text)

Max Activating Token Index: 530

Text #17

Max Range: 5.4022. Min Range: -5.4022

Max Act: 5.2332. Min Act: -0.1700

Data Index: 6253637 (Open Web Text)

Max Activating Token Index: 702

Text #18

Max Range: 5.4022. Min Range: -5.4022

Max Act: 5.2666. Min Act: -0.1700

Data Index: 3886696 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 5.4022. Min Range: -5.4022

Max Act: 5.2221. Min Act: -0.1700

Data Index: 6454202 (Open Web Text)

Max Activating Token Index: 210