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

Dataset: Open Web Text

Neuron 1073 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: 1.8406. Min Range: -1.8406

Max Act: 1.8406. Min Act: -0.1700

Data Index: 3564249 (Open Web Text)

Max Activating Token Index: 157

Text #1

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7799. Min Act: -0.1700

Data Index: 2503074 (Open Web Text)

Max Activating Token Index: 921

Text #2

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7775. Min Act: -0.1700

Data Index: 6748340 (Open Web Text)

Max Activating Token Index: 310

Text #3

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7712. Min Act: -0.1667

Data Index: 6570133 (Open Web Text)

Max Activating Token Index: 16

Text #4

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7305. Min Act: -0.1700

Data Index: 4579147 (Open Web Text)

Max Activating Token Index: 1001

Text #5

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7456. Min Act: -0.1694

Data Index: 7062074 (Open Web Text)

Max Activating Token Index: 479

Text #6

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7373. Min Act: -0.1684

Data Index: 4806646 (Open Web Text)

Max Activating Token Index: 345

Text #7

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7238. Min Act: -0.1700

Data Index: 4248662 (Open Web Text)

Max Activating Token Index: 562

Text #8

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7444. Min Act: -0.1700

Data Index: 2765720 (Open Web Text)

Max Activating Token Index: 757

Text #9

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7346. Min Act: -0.1700

Data Index: 2732524 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7262. Min Act: -0.1700

Data Index: 4739387 (Open Web Text)

Max Activating Token Index: 89

Text #11

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7618. Min Act: -0.1700

Data Index: 7102251 (Open Web Text)

Max Activating Token Index: 661

Text #12

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7250. Min Act: -0.1700

Data Index: 3789933 (Open Web Text)

Max Activating Token Index: 620

Text #13

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7193. Min Act: -0.1700

Data Index: 8475454 (Open Web Text)

Max Activating Token Index: 261

Text #14

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7168. Min Act: -0.1700

Data Index: 470517 (Open Web Text)

Max Activating Token Index: 261

Text #15

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7245. Min Act: -0.1700

Data Index: 42662 (Open Web Text)

Max Activating Token Index: 493

Text #16

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7218. Min Act: -0.1700

Data Index: 3112953 (Open Web Text)

Max Activating Token Index: 436

Text #17

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7071. Min Act: -0.1694

Data Index: 4173976 (Open Web Text)

Max Activating Token Index: 42

Text #18

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7064. Min Act: -0.1700

Data Index: 2554521 (Open Web Text)

Max Activating Token Index: 25

Text #19

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.6774. Min Act: -0.1700

Data Index: 1040273 (Open Web Text)

Max Activating Token Index: 946