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

Dataset: Open Web Text

Neuron 1060 in Layer 5

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: 3.7863. Min Range: -3.7863

Max Act: 3.7863. Min Act: -0.1700

Data Index: 797119 (Open Web Text)

Max Activating Token Index: 530

Text #1

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7071. Min Act: -0.1700

Data Index: 6311533 (Open Web Text)

Max Activating Token Index: 317

Text #2

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7247. Min Act: -0.1700

Data Index: 3828795 (Open Web Text)

Max Activating Token Index: 907

Text #3

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.6987. Min Act: -0.1700

Data Index: 1642889 (Open Web Text)

Max Activating Token Index: 891

Text #4

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.6841. Min Act: -0.1700

Data Index: 1271884 (Open Web Text)

Max Activating Token Index: 246

Text #5

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7161. Min Act: -0.1700

Data Index: 4820014 (Open Web Text)

Max Activating Token Index: 147

Text #6

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.6690. Min Act: -0.1700

Data Index: 8747573 (Open Web Text)

Max Activating Token Index: 915

Text #7

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.6582. Min Act: -0.1700

Data Index: 8821813 (Open Web Text)

Max Activating Token Index: 332

Text #8

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.6358. Min Act: -0.1700

Data Index: 8192368 (Open Web Text)

Max Activating Token Index: 367

Text #9

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.6372. Min Act: -0.1700

Data Index: 4427227 (Open Web Text)

Max Activating Token Index: 26

Text #10

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.6326. Min Act: -0.1700

Data Index: 4696490 (Open Web Text)

Max Activating Token Index: 864

Text #11

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.6723. Min Act: -0.1700

Data Index: 4427212 (Open Web Text)

Max Activating Token Index: 508

Text #12

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.6376. Min Act: -0.1700

Data Index: 6438315 (Open Web Text)

Max Activating Token Index: 146

Text #13

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.6144. Min Act: -0.1700

Data Index: 2857222 (Open Web Text)

Max Activating Token Index: 496

Text #14

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.6052. Min Act: -0.1700

Data Index: 593200 (Open Web Text)

Max Activating Token Index: 724

Text #15

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.6204. Min Act: -0.1700

Data Index: 5491970 (Open Web Text)

Max Activating Token Index: 707

Text #16

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.6155. Min Act: -0.1700

Data Index: 3191205 (Open Web Text)

Max Activating Token Index: 120

Text #17

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.6175. Min Act: -0.1700

Data Index: 6555796 (Open Web Text)

Max Activating Token Index: 719

Text #18

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.5866. Min Act: -0.1700

Data Index: 1424794 (Open Web Text)

Max Activating Token Index: 672

Text #19

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.6274. Min Act: -0.1700

Data Index: 1114689 (Open Web Text)

Max Activating Token Index: 1014