Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2885 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.3523. Min Range: -4.3523

Max Act: 4.0633. Min Act: -0.0000

Data Index: 552600 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 4.3523. Min Range: -4.3523

Max Act: 4.3523. Min Act: -0.0000

Data Index: 175461 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 4.3523. Min Range: -4.3523

Max Act: 3.6294. Min Act: -0.0000

Data Index: 699214 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 4.3523. Min Range: -4.3523

Max Act: 4.0030. Min Act: -0.0000

Data Index: 296079 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 4.3523. Min Range: -4.3523

Max Act: 3.4801. Min Act: -0.0000

Data Index: 915039 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 4.3523. Min Range: -4.3523

Max Act: 3.6968. Min Act: -0.0000

Data Index: 1021225 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 4.3523. Min Range: -4.3523

Max Act: 3.5106. Min Act: -0.0000

Data Index: 975925 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 4.3523. Min Range: -4.3523

Max Act: 3.3121. Min Act: -0.0000

Data Index: 1097834 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 4.3523. Min Range: -4.3523

Max Act: 3.5115. Min Act: -0.0000

Data Index: 104510 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 4.3523. Min Range: -4.3523

Max Act: 3.2214. Min Act: -0.0000

Data Index: 581098 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 4.3523. Min Range: -4.3523

Max Act: 3.4870. Min Act: -0.0000

Data Index: 1073692 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 4.3523. Min Range: -4.3523

Max Act: 3.1776. Min Act: -0.0000

Data Index: 1244039 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 4.3523. Min Range: -4.3523

Max Act: 3.1380. Min Act: -0.0000

Data Index: 1110853 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 4.3523. Min Range: -4.3523

Max Act: 3.0215. Min Act: -0.0000

Data Index: 783274 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 4.3523. Min Range: -4.3523

Max Act: 2.9009. Min Act: -0.0000

Data Index: 800026 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 4.3523. Min Range: -4.3523

Max Act: 2.7301. Min Act: -0.0000

Data Index: 1258285 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 4.3523. Min Range: -4.3523

Max Act: 2.9451. Min Act: -0.0000

Data Index: 709309 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 4.3523. Min Range: -4.3523

Max Act: 3.0872. Min Act: -0.0000

Data Index: 536501 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 4.3523. Min Range: -4.3523

Max Act: 3.0596. Min Act: -0.0000

Data Index: 680789 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 4.3523. Min Range: -4.3523

Max Act: 3.0493. Min Act: -0.0000

Data Index: 149044 (C4 (Web Text))

Max Activating Token Index: 362