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

Dataset: Open Web Text

Neuron 998 in Layer 6

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: 4.3414. Min Range: -4.3414

Max Act: 4.3414. Min Act: -0.1700

Data Index: 2951418 (Open Web Text)

Max Activating Token Index: 344

Text #1

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.1634. Min Act: -0.1700

Data Index: 3244693 (Open Web Text)

Max Activating Token Index: 319

Text #2

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0857. Min Act: -0.1700

Data Index: 3076397 (Open Web Text)

Max Activating Token Index: 615

Text #3

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0841. Min Act: -0.1700

Data Index: 7540598 (Open Web Text)

Max Activating Token Index: 636

Text #4

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0383. Min Act: -0.1700

Data Index: 1280416 (Open Web Text)

Max Activating Token Index: 717

Text #5

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0314. Min Act: -0.1700

Data Index: 4580051 (Open Web Text)

Max Activating Token Index: 621

Text #6

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0384. Min Act: -0.1700

Data Index: 7505720 (Open Web Text)

Max Activating Token Index: 480

Text #7

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0098. Min Act: -0.1700

Data Index: 5980436 (Open Web Text)

Max Activating Token Index: 345

Text #8

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0171. Min Act: -0.1700

Data Index: 2390841 (Open Web Text)

Max Activating Token Index: 427

Text #9

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0102. Min Act: -0.1700

Data Index: 1626980 (Open Web Text)

Max Activating Token Index: 414

Text #10

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0270. Min Act: -0.1700

Data Index: 588989 (Open Web Text)

Max Activating Token Index: 346

Text #11

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0114. Min Act: -0.1700

Data Index: 8129539 (Open Web Text)

Max Activating Token Index: 214

Text #12

Max Range: 4.3414. Min Range: -4.3414

Max Act: 4.0020. Min Act: -0.1700

Data Index: 4440878 (Open Web Text)

Max Activating Token Index: 983

Text #13

Max Range: 4.3414. Min Range: -4.3414

Max Act: 3.9544. Min Act: -0.1700

Data Index: 8319765 (Open Web Text)

Max Activating Token Index: 153

Text #14

Max Range: 4.3414. Min Range: -4.3414

Max Act: 3.9342. Min Act: -0.1700

Data Index: 8321069 (Open Web Text)

Max Activating Token Index: 713

Text #15

Max Range: 4.3414. Min Range: -4.3414

Max Act: 3.9463. Min Act: -0.1700

Data Index: 1407772 (Open Web Text)

Max Activating Token Index: 170

Text #16

Max Range: 4.3414. Min Range: -4.3414

Max Act: 3.9700. Min Act: -0.1700

Data Index: 2043290 (Open Web Text)

Max Activating Token Index: 652

Text #17

Max Range: 4.3414. Min Range: -4.3414

Max Act: 3.9591. Min Act: -0.1700

Data Index: 4301394 (Open Web Text)

Max Activating Token Index: 949

Text #18

Max Range: 4.3414. Min Range: -4.3414

Max Act: 3.9231. Min Act: -0.1700

Data Index: 3087732 (Open Web Text)

Max Activating Token Index: 528

Text #19

Max Range: 4.3414. Min Range: -4.3414

Max Act: 3.9691. Min Act: -0.1700

Data Index: 3096437 (Open Web Text)

Max Activating Token Index: 621