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

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

Neuron 3474 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.1379. Min Act: -0.0000

Data Index: 87984 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.7963. Min Act: -0.0000

Data Index: 563868 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.7057. Min Act: -0.0000

Data Index: 763755 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.6139. Min Act: -0.0000

Data Index: 1351031 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.7227. Min Act: -0.0000

Data Index: 383819 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.7015. Min Act: -0.0000

Data Index: 10610 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.6892. Min Act: -0.0000

Data Index: 945396 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.7095. Min Act: -0.0000

Data Index: 1151947 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.6851. Min Act: -0.0000

Data Index: 795503 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1003543 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.7445. Min Act: -0.0000

Data Index: 113285 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1305347 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.4423. Min Act: -0.0000

Data Index: 563777 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.6369. Min Act: -0.0000

Data Index: 824774 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.5555. Min Act: -0.0000

Data Index: 706359 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.5465. Min Act: -0.0000

Data Index: 253543 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.6150. Min Act: -0.0000

Data Index: 112419 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.6090. Min Act: -0.0000

Data Index: 954332 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.6093. Min Act: -0.0000

Data Index: 89984 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 1.1379. Min Range: -1.1379

Max Act: 0.5923. Min Act: -0.0000

Data Index: 137282 (C4 (Web Text))

Max Activating Token Index: 959