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

Dataset: Open Web Text

Neuron 101 in Layer 2

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: 3.6179. Min Range: -3.6179

Max Act: 3.6179. Min Act: -0.1700

Data Index: 5275583 (Open Web Text)

Max Activating Token Index: 933

Text #1

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.6121. Min Act: -0.1700

Data Index: 8567973 (Open Web Text)

Max Activating Token Index: 135

Text #2

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5859. Min Act: -0.1700

Data Index: 537371 (Open Web Text)

Max Activating Token Index: 47

Text #3

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5993. Min Act: -0.1700

Data Index: 6060532 (Open Web Text)

Max Activating Token Index: 512

Text #4

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5821. Min Act: -0.1700

Data Index: 4184517 (Open Web Text)

Max Activating Token Index: 263

Text #5

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5636. Min Act: -0.1700

Data Index: 370000 (Open Web Text)

Max Activating Token Index: 413

Text #6

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5480. Min Act: -0.1700

Data Index: 501575 (Open Web Text)

Max Activating Token Index: 374

Text #7

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5552. Min Act: -0.1700

Data Index: 8792907 (Open Web Text)

Max Activating Token Index: 322

Text #8

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5698. Min Act: -0.1700

Data Index: 261235 (Open Web Text)

Max Activating Token Index: 363

Text #9

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5591. Min Act: -0.1700

Data Index: 1602762 (Open Web Text)

Max Activating Token Index: 612

Text #10

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5724. Min Act: -0.1700

Data Index: 5612712 (Open Web Text)

Max Activating Token Index: 445

Text #11

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5716. Min Act: -0.1700

Data Index: 45772 (Open Web Text)

Max Activating Token Index: 995

Text #12

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5507. Min Act: -0.1700

Data Index: 1577042 (Open Web Text)

Max Activating Token Index: 106

Text #13

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5278. Min Act: -0.1700

Data Index: 5946291 (Open Web Text)

Max Activating Token Index: 674

Text #14

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5164. Min Act: -0.1700

Data Index: 3128746 (Open Web Text)

Max Activating Token Index: 601

Text #15

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5464. Min Act: -0.1700

Data Index: 2329596 (Open Web Text)

Max Activating Token Index: 47

Text #16

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5222. Min Act: -0.1700

Data Index: 5932351 (Open Web Text)

Max Activating Token Index: 24

Text #17

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5188. Min Act: -0.1700

Data Index: 5803185 (Open Web Text)

Max Activating Token Index: 151

Text #18

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5312. Min Act: -0.1700

Data Index: 5612710 (Open Web Text)

Max Activating Token Index: 725

Text #19

Max Range: 3.6179. Min Range: -3.6179

Max Act: 3.5259. Min Act: -0.1700

Data Index: 151122 (Open Web Text)

Max Activating Token Index: 901