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

Dataset: Open Web Text

Neuron 1828 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: 1.6667. Min Range: -1.6667

Max Act: 1.6624. Min Act: -0.1700

Data Index: 8487995 (Open Web Text)

Max Activating Token Index: 151

Text #1

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6667. Min Act: -0.1700

Data Index: 7299647 (Open Web Text)

Max Activating Token Index: 238

Text #2

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6526. Min Act: -0.1700

Data Index: 3318581 (Open Web Text)

Max Activating Token Index: 962

Text #3

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6416. Min Act: -0.1700

Data Index: 3252252 (Open Web Text)

Max Activating Token Index: 981

Text #4

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6426. Min Act: -0.1700

Data Index: 85238 (Open Web Text)

Max Activating Token Index: 599

Text #5

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6318. Min Act: -0.1698

Data Index: 6095527 (Open Web Text)

Max Activating Token Index: 686

Text #6

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6295. Min Act: -0.1700

Data Index: 8478656 (Open Web Text)

Max Activating Token Index: 363

Text #7

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6327. Min Act: -0.1700

Data Index: 1759517 (Open Web Text)

Max Activating Token Index: 645

Text #8

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6252. Min Act: -0.1700

Data Index: 2837070 (Open Web Text)

Max Activating Token Index: 995

Text #9

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6223. Min Act: -0.1700

Data Index: 1901219 (Open Web Text)

Max Activating Token Index: 985

Text #10

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6112. Min Act: -0.1700

Data Index: 8225385 (Open Web Text)

Max Activating Token Index: 590

Text #11

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6163. Min Act: -0.1700

Data Index: 6330884 (Open Web Text)

Max Activating Token Index: 780

Text #12

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6180. Min Act: -0.1700

Data Index: 7855672 (Open Web Text)

Max Activating Token Index: 457

Text #13

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6190. Min Act: -0.1700

Data Index: 6269280 (Open Web Text)

Max Activating Token Index: 642

Text #14

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6195. Min Act: -0.1700

Data Index: 7693067 (Open Web Text)

Max Activating Token Index: 978

Text #15

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6120. Min Act: -0.1700

Data Index: 94092 (Open Web Text)

Max Activating Token Index: 950

Text #16

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6158. Min Act: -0.1700

Data Index: 6246063 (Open Web Text)

Max Activating Token Index: 521

Text #17

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6201. Min Act: -0.1700

Data Index: 4611291 (Open Web Text)

Max Activating Token Index: 556

Text #18

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6160. Min Act: -0.1700

Data Index: 4412753 (Open Web Text)

Max Activating Token Index: 624

Text #19

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6095. Min Act: -0.1700

Data Index: 7690421 (Open Web Text)

Max Activating Token Index: 49