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

Dataset: Open Web Text

Neuron 1739 in Layer 3

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: 3.3370. Min Range: -3.3370

Max Act: 3.3370. Min Act: -0.1700

Data Index: 2759351 (Open Web Text)

Max Activating Token Index: 25

Text #1

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.3118. Min Act: -0.1700

Data Index: 4062754 (Open Web Text)

Max Activating Token Index: 288

Text #2

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.3137. Min Act: -0.1700

Data Index: 3537828 (Open Web Text)

Max Activating Token Index: 89

Text #3

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.3057. Min Act: -0.1700

Data Index: 6710252 (Open Web Text)

Max Activating Token Index: 483

Text #4

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.2731. Min Act: -0.1700

Data Index: 5461291 (Open Web Text)

Max Activating Token Index: 32

Text #5

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.2622. Min Act: -0.1700

Data Index: 6907985 (Open Web Text)

Max Activating Token Index: 700

Text #6

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.2810. Min Act: -0.1700

Data Index: 8254840 (Open Web Text)

Max Activating Token Index: 419

Text #7

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.2314. Min Act: -0.1700

Data Index: 4650961 (Open Web Text)

Max Activating Token Index: 113

Text #8

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.2357. Min Act: -0.1700

Data Index: 5075402 (Open Web Text)

Max Activating Token Index: 19

Text #9

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.2086. Min Act: -0.1700

Data Index: 8517337 (Open Web Text)

Max Activating Token Index: 379

Text #10

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.2051. Min Act: -0.1700

Data Index: 5728471 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.2184. Min Act: -0.1700

Data Index: 8097330 (Open Web Text)

Max Activating Token Index: 505

Text #12

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.2103. Min Act: -0.1700

Data Index: 7492666 (Open Web Text)

Max Activating Token Index: 535

Text #13

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.1929. Min Act: -0.1700

Data Index: 2817389 (Open Web Text)

Max Activating Token Index: 415

Text #14

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.1797. Min Act: -0.1700

Data Index: 5235116 (Open Web Text)

Max Activating Token Index: 654

Text #15

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.1852. Min Act: -0.1700

Data Index: 8492919 (Open Web Text)

Max Activating Token Index: 1018

Text #16

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.1728. Min Act: -0.1700

Data Index: 7069761 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.1730. Min Act: -0.1700

Data Index: 8559164 (Open Web Text)

Max Activating Token Index: 506

Text #18

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.1757. Min Act: -0.1700

Data Index: 7467726 (Open Web Text)

Max Activating Token Index: 816

Text #19

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.1724. Min Act: -0.1700

Data Index: 6796187 (Open Web Text)

Max Activating Token Index: 406