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

Dataset: Open Web Text

Neuron 2821 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: 1.6162. Min Range: -1.6162

Max Act: 1.6162. Min Act: -0.1700

Data Index: 5226381 (Open Web Text)

Max Activating Token Index: 742

Text #1

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.5787. Min Act: -0.1700

Data Index: 6078275 (Open Web Text)

Max Activating Token Index: 506

Text #2

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.5662. Min Act: -0.1700

Data Index: 8232306 (Open Web Text)

Max Activating Token Index: 383

Text #3

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.5406. Min Act: -0.1700

Data Index: 4512206 (Open Web Text)

Max Activating Token Index: 543

Text #4

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.5541. Min Act: -0.1700

Data Index: 548024 (Open Web Text)

Max Activating Token Index: 310

Text #5

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.5464. Min Act: -0.1700

Data Index: 4083558 (Open Web Text)

Max Activating Token Index: 566

Text #6

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.5484. Min Act: -0.1700

Data Index: 104086 (Open Web Text)

Max Activating Token Index: 487

Text #7

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.5352. Min Act: -0.1700

Data Index: 5117490 (Open Web Text)

Max Activating Token Index: 61

Text #8

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.5336. Min Act: -0.1700

Data Index: 2808986 (Open Web Text)

Max Activating Token Index: 261

Text #9

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.5225. Min Act: -0.1700

Data Index: 2622631 (Open Web Text)

Max Activating Token Index: 417

Text #10

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.5229. Min Act: -0.1700

Data Index: 8419703 (Open Web Text)

Max Activating Token Index: 624

Text #11

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.5320. Min Act: -0.1700

Data Index: 6360346 (Open Web Text)

Max Activating Token Index: 316

Text #12

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.5385. Min Act: -0.1700

Data Index: 3597772 (Open Web Text)

Max Activating Token Index: 860

Text #13

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.5274. Min Act: -0.1700

Data Index: 746645 (Open Web Text)

Max Activating Token Index: 538

Text #14

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.5396. Min Act: -0.1700

Data Index: 435711 (Open Web Text)

Max Activating Token Index: 523

Text #15

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.5105. Min Act: -0.1700

Data Index: 7998386 (Open Web Text)

Max Activating Token Index: 677

Text #16

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.5186. Min Act: -0.1700

Data Index: 400891 (Open Web Text)

Max Activating Token Index: 344

Text #17

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.4998. Min Act: -0.1700

Data Index: 8649782 (Open Web Text)

Max Activating Token Index: 717

Text #18

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.5202. Min Act: -0.1700

Data Index: 8707525 (Open Web Text)

Max Activating Token Index: 455

Text #19

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.5088. Min Act: -0.1700

Data Index: 4872276 (Open Web Text)

Max Activating Token Index: 702