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

Dataset: Open Web Text

Neuron 3031 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: 3.1199. Min Range: -3.1199

Max Act: 3.1199. Min Act: -0.1700

Data Index: 8131050 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.1075. Min Act: -0.1700

Data Index: 4233212 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0718. Min Act: -0.1700

Data Index: 7780326 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0641. Min Act: -0.1700

Data Index: 3228441 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0461. Min Act: -0.1700

Data Index: 6446435 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0391. Min Act: -0.1700

Data Index: 2418678 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0391. Min Act: -0.1700

Data Index: 4276435 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0504. Min Act: -0.1700

Data Index: 7890635 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0386. Min Act: -0.1700

Data Index: 8736294 (Open Web Text)

Max Activating Token Index: 279

Text #9

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0381. Min Act: -0.1700

Data Index: 1965829 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0455. Min Act: -0.1700

Data Index: 5839032 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0437. Min Act: -0.1700

Data Index: 5155244 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0566. Min Act: -0.1700

Data Index: 3446378 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0390. Min Act: -0.1700

Data Index: 571949 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0310. Min Act: -0.1700

Data Index: 5389978 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0232. Min Act: -0.1700

Data Index: 588230 (Open Web Text)

Max Activating Token Index: 358

Text #16

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0275. Min Act: -0.1700

Data Index: 1020229 (Open Web Text)

Max Activating Token Index: 865

Text #17

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0254. Min Act: -0.1700

Data Index: 3401718 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0222. Min Act: -0.1700

Data Index: 3363579 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.1199. Min Range: -3.1199

Max Act: 3.0326. Min Act: -0.1700

Data Index: 5124338 (Open Web Text)

Max Activating Token Index: 660