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

Dataset: Open Web Text

Neuron 2404 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: 1.6362. Min Range: -1.6362

Max Act: 1.6362. Min Act: -0.1700

Data Index: 2669806 (Open Web Text)

Max Activating Token Index: 172

Text #1

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5963. Min Act: -0.1700

Data Index: 6458391 (Open Web Text)

Max Activating Token Index: 249

Text #2

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5757. Min Act: -0.1699

Data Index: 4541182 (Open Web Text)

Max Activating Token Index: 137

Text #3

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5908. Min Act: -0.1700

Data Index: 7059426 (Open Web Text)

Max Activating Token Index: 625

Text #4

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5774. Min Act: -0.1700

Data Index: 4760585 (Open Web Text)

Max Activating Token Index: 442

Text #5

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5717. Min Act: -0.1697

Data Index: 1021186 (Open Web Text)

Max Activating Token Index: 112

Text #6

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5583. Min Act: -0.1700

Data Index: 5507099 (Open Web Text)

Max Activating Token Index: 349

Text #7

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5495. Min Act: -0.1700

Data Index: 7974249 (Open Web Text)

Max Activating Token Index: 97

Text #8

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5381. Min Act: -0.1700

Data Index: 3802492 (Open Web Text)

Max Activating Token Index: 618

Text #9

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5430. Min Act: -0.1700

Data Index: 6355787 (Open Web Text)

Max Activating Token Index: 558

Text #10

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5399. Min Act: -0.1688

Data Index: 236118 (Open Web Text)

Max Activating Token Index: 244

Text #11

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5331. Min Act: -0.1699

Data Index: 7655089 (Open Web Text)

Max Activating Token Index: 254

Text #12

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5297. Min Act: -0.1700

Data Index: 3290127 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5173. Min Act: -0.1700

Data Index: 7846910 (Open Web Text)

Max Activating Token Index: 79

Text #14

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5266. Min Act: -0.1700

Data Index: 1848635 (Open Web Text)

Max Activating Token Index: 686

Text #15

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5220. Min Act: -0.1700

Data Index: 1387096 (Open Web Text)

Max Activating Token Index: 685

Text #16

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5213. Min Act: -0.1700

Data Index: 5845220 (Open Web Text)

Max Activating Token Index: 257

Text #17

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5189. Min Act: -0.1700

Data Index: 2564775 (Open Web Text)

Max Activating Token Index: 657

Text #18

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5219. Min Act: -0.1700

Data Index: 3743607 (Open Web Text)

Max Activating Token Index: 446

Text #19

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5034. Min Act: -0.1700

Data Index: 8816165 (Open Web Text)

Max Activating Token Index: 663