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

Dataset: Open Web Text

Neuron 65 in Layer 1

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: 3.2313. Min Range: -3.2313

Max Act: 3.2313. Min Act: -0.1700

Data Index: 4349664 (Open Web Text)

Max Activating Token Index: 489

Text #1

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.1335. Min Act: -0.1700

Data Index: 5327500 (Open Web Text)

Max Activating Token Index: 532

Text #2

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.1078. Min Act: -0.1700

Data Index: 4349659 (Open Web Text)

Max Activating Token Index: 915

Text #3

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.1058. Min Act: -0.1700

Data Index: 1002966 (Open Web Text)

Max Activating Token Index: 786

Text #4

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.1150. Min Act: -0.1700

Data Index: 4723000 (Open Web Text)

Max Activating Token Index: 207

Text #5

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0662. Min Act: -0.1700

Data Index: 3101450 (Open Web Text)

Max Activating Token Index: 580

Text #6

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0550. Min Act: -0.1700

Data Index: 891821 (Open Web Text)

Max Activating Token Index: 997

Text #7

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0462. Min Act: -0.1700

Data Index: 715233 (Open Web Text)

Max Activating Token Index: 993

Text #8

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0383. Min Act: -0.1700

Data Index: 873808 (Open Web Text)

Max Activating Token Index: 998

Text #9

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0322. Min Act: -0.1700

Data Index: 5150667 (Open Web Text)

Max Activating Token Index: 49

Text #10

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0418. Min Act: -0.1700

Data Index: 6561902 (Open Web Text)

Max Activating Token Index: 196

Text #11

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0398. Min Act: -0.1700

Data Index: 7875552 (Open Web Text)

Max Activating Token Index: 145

Text #12

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0255. Min Act: -0.1700

Data Index: 566024 (Open Web Text)

Max Activating Token Index: 416

Text #13

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0080. Min Act: -0.1700

Data Index: 4867861 (Open Web Text)

Max Activating Token Index: 389

Text #14

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0167. Min Act: -0.1700

Data Index: 4444318 (Open Web Text)

Max Activating Token Index: 564

Text #15

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0213. Min Act: -0.1700

Data Index: 6824012 (Open Web Text)

Max Activating Token Index: 199

Text #16

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0107. Min Act: -0.1700

Data Index: 3899563 (Open Web Text)

Max Activating Token Index: 261

Text #17

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0202. Min Act: -0.1700

Data Index: 794793 (Open Web Text)

Max Activating Token Index: 495

Text #18

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0078. Min Act: -0.1700

Data Index: 348528 (Open Web Text)

Max Activating Token Index: 624

Text #19

Max Range: 3.2313. Min Range: -3.2313

Max Act: 2.9947. Min Act: -0.1700

Data Index: 773660 (Open Web Text)

Max Activating Token Index: 64