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

Dataset: Open Web Text

Neuron 164 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: 1.9342. Min Range: -1.9342

Max Act: 1.9335. Min Act: -0.1700

Data Index: 2425212 (Open Web Text)

Max Activating Token Index: 351

Text #1

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.9342. Min Act: -0.1700

Data Index: 968912 (Open Web Text)

Max Activating Token Index: 76

Text #2

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.9030. Min Act: -0.1700

Data Index: 7495800 (Open Web Text)

Max Activating Token Index: 455

Text #3

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.8761. Min Act: -0.1700

Data Index: 3897482 (Open Web Text)

Max Activating Token Index: 1022

Text #4

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.8640. Min Act: -0.1700

Data Index: 1898653 (Open Web Text)

Max Activating Token Index: 264

Text #5

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.8668. Min Act: -0.1699

Data Index: 984152 (Open Web Text)

Max Activating Token Index: 692

Text #6

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.8461. Min Act: -0.1700

Data Index: 2474262 (Open Web Text)

Max Activating Token Index: 738

Text #7

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.8666. Min Act: -0.1700

Data Index: 319802 (Open Web Text)

Max Activating Token Index: 136

Text #8

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.8411. Min Act: -0.1700

Data Index: 7734421 (Open Web Text)

Max Activating Token Index: 257

Text #9

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.8372. Min Act: -0.1699

Data Index: 2770519 (Open Web Text)

Max Activating Token Index: 890

Text #10

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.8488. Min Act: -0.1700

Data Index: 8621330 (Open Web Text)

Max Activating Token Index: 328

Text #11

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.8332. Min Act: -0.1700

Data Index: 8454769 (Open Web Text)

Max Activating Token Index: 414

Text #12

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.8311. Min Act: -0.1700

Data Index: 3619240 (Open Web Text)

Max Activating Token Index: 224

Text #13

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.8362. Min Act: -0.1700

Data Index: 6135440 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.8435. Min Act: -0.1700

Data Index: 2084555 (Open Web Text)

Max Activating Token Index: 483

Text #15

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.8280. Min Act: -0.1700

Data Index: 7078435 (Open Web Text)

Max Activating Token Index: 417

Text #16

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.8193. Min Act: -0.1700

Data Index: 6955621 (Open Web Text)

Max Activating Token Index: 386

Text #17

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.8320. Min Act: -0.1700

Data Index: 6832490 (Open Web Text)

Max Activating Token Index: 802

Text #18

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.8205. Min Act: -0.1700

Data Index: 4937446 (Open Web Text)

Max Activating Token Index: 748

Text #19

Max Range: 1.9342. Min Range: -1.9342

Max Act: 1.8013. Min Act: -0.1700

Data Index: 4926141 (Open Web Text)

Max Activating Token Index: 367