Model: GELU Model: 2 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 328 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.7037. Min Act: -0.1700

Data Index: 595711 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.6881. Min Act: -0.1700

Data Index: 894643 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.6881. Min Act: -0.1700

Data Index: 431019 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.6724. Min Act: -0.1700

Data Index: 591070 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.6724. Min Act: -0.1700

Data Index: 1303914 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.6724. Min Act: -0.1700

Data Index: 637093 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.6724. Min Act: -0.1700

Data Index: 1344645 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.6411. Min Act: -0.1700

Data Index: 574078 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.6568. Min Act: -0.1700

Data Index: 938174 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.6568. Min Act: -0.1700

Data Index: 265975 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.6568. Min Act: -0.1700

Data Index: 1857 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.6255. Min Act: -0.1700

Data Index: 1206646 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.6255. Min Act: -0.1700

Data Index: 387465 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.6411. Min Act: -0.1700

Data Index: 526714 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.6411. Min Act: -0.1700

Data Index: 127397 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.6255. Min Act: -0.1700

Data Index: 262536 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.6098. Min Act: -0.1700

Data Index: 332287 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.6098. Min Act: -0.1700

Data Index: 666143 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.5941. Min Act: -0.1700

Data Index: 811765 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 3.7037. Min Range: -3.7037

Max Act: 3.6098. Min Act: -0.1700

Data Index: 429537 (C4 (Web Text))

Max Activating Token Index: 858