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

Dataset: Open Web Text

Neuron 515 in Layer 4

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: 3.1733. Min Range: -3.1733

Max Act: 3.1428. Min Act: -0.1700

Data Index: 492599 (Open Web Text)

Max Activating Token Index: 676

Text #1

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.1733. Min Act: -0.1700

Data Index: 4095357 (Open Web Text)

Max Activating Token Index: 450

Text #2

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.1392. Min Act: -0.1700

Data Index: 5306220 (Open Web Text)

Max Activating Token Index: 317

Text #3

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.1502. Min Act: -0.1700

Data Index: 898000 (Open Web Text)

Max Activating Token Index: 430

Text #4

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.1221. Min Act: -0.1700

Data Index: 4801094 (Open Web Text)

Max Activating Token Index: 648

Text #5

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.0997. Min Act: -0.1700

Data Index: 7514370 (Open Web Text)

Max Activating Token Index: 954

Text #6

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.1131. Min Act: -0.1700

Data Index: 693283 (Open Web Text)

Max Activating Token Index: 410

Text #7

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.1158. Min Act: -0.1700

Data Index: 7256380 (Open Web Text)

Max Activating Token Index: 651

Text #8

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.1005. Min Act: -0.1700

Data Index: 4667511 (Open Web Text)

Max Activating Token Index: 421

Text #9

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.0803. Min Act: -0.1700

Data Index: 2932262 (Open Web Text)

Max Activating Token Index: 587

Text #10

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.0643. Min Act: -0.1700

Data Index: 238789 (Open Web Text)

Max Activating Token Index: 379

Text #11

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.0712. Min Act: -0.1700

Data Index: 3039557 (Open Web Text)

Max Activating Token Index: 107

Text #12

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.0929. Min Act: -0.1700

Data Index: 969279 (Open Web Text)

Max Activating Token Index: 426

Text #13

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.0610. Min Act: -0.1700

Data Index: 4804768 (Open Web Text)

Max Activating Token Index: 397

Text #14

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.0674. Min Act: -0.1700

Data Index: 4125223 (Open Web Text)

Max Activating Token Index: 854

Text #15

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.0554. Min Act: -0.1700

Data Index: 4711779 (Open Web Text)

Max Activating Token Index: 257

Text #16

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.0589. Min Act: -0.1700

Data Index: 7154428 (Open Web Text)

Max Activating Token Index: 503

Text #17

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.0742. Min Act: -0.1700

Data Index: 6585224 (Open Web Text)

Max Activating Token Index: 976

Text #18

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.0379. Min Act: -0.1700

Data Index: 3380386 (Open Web Text)

Max Activating Token Index: 667

Text #19

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.0302. Min Act: -0.1700

Data Index: 4271999 (Open Web Text)

Max Activating Token Index: 472