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

Dataset: Open Web Text

Neuron 371 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: 3.5509. Min Range: -3.5509

Max Act: 3.5509. Min Act: -0.1700

Data Index: 1679292 (Open Web Text)

Max Activating Token Index: 602

Text #1

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.5181. Min Act: -0.1700

Data Index: 3639975 (Open Web Text)

Max Activating Token Index: 401

Text #2

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.4564. Min Act: -0.1700

Data Index: 3702906 (Open Web Text)

Max Activating Token Index: 200

Text #3

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.4662. Min Act: -0.1700

Data Index: 8192020 (Open Web Text)

Max Activating Token Index: 848

Text #4

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.4308. Min Act: -0.1700

Data Index: 8421041 (Open Web Text)

Max Activating Token Index: 463

Text #5

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.4266. Min Act: -0.1700

Data Index: 3710155 (Open Web Text)

Max Activating Token Index: 152

Text #6

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.4183. Min Act: -0.1700

Data Index: 6589596 (Open Web Text)

Max Activating Token Index: 119

Text #7

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.3975. Min Act: -0.1700

Data Index: 5303714 (Open Web Text)

Max Activating Token Index: 388

Text #8

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.3871. Min Act: -0.1700

Data Index: 8421039 (Open Web Text)

Max Activating Token Index: 313

Text #9

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.3829. Min Act: -0.1700

Data Index: 1065615 (Open Web Text)

Max Activating Token Index: 386

Text #10

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.3526. Min Act: -0.1700

Data Index: 1968778 (Open Web Text)

Max Activating Token Index: 536

Text #11

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.3688. Min Act: -0.1700

Data Index: 1480647 (Open Web Text)

Max Activating Token Index: 544

Text #12

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.3514. Min Act: -0.1700

Data Index: 1372662 (Open Web Text)

Max Activating Token Index: 456

Text #13

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.3581. Min Act: -0.1700

Data Index: 8417956 (Open Web Text)

Max Activating Token Index: 359

Text #14

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.3654. Min Act: -0.1700

Data Index: 6909283 (Open Web Text)

Max Activating Token Index: 169

Text #15

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.3443. Min Act: -0.1700

Data Index: 8048512 (Open Web Text)

Max Activating Token Index: 309

Text #16

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.3331. Min Act: -0.1700

Data Index: 1203186 (Open Web Text)

Max Activating Token Index: 389

Text #17

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.3159. Min Act: -0.1700

Data Index: 748298 (Open Web Text)

Max Activating Token Index: 688

Text #18

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.3152. Min Act: -0.1700

Data Index: 4095556 (Open Web Text)

Max Activating Token Index: 586

Text #19

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.3180. Min Act: -0.1700

Data Index: 2273290 (Open Web Text)

Max Activating Token Index: 650