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

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

Neuron 3904 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: 0.8637. Min Range: -0.8637

Max Act: 0.8483. Min Act: -0.0000

Data Index: 760841 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.8637. Min Act: -0.0000

Data Index: 49177 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.8195. Min Act: -0.0000

Data Index: 1150765 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7736. Min Act: -0.0000

Data Index: 531489 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7748. Min Act: -0.0000

Data Index: 1222486 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7604. Min Act: -0.0000

Data Index: 387194 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7343. Min Act: -0.0000

Data Index: 793828 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7316. Min Act: -0.0000

Data Index: 460044 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7547. Min Act: -0.0000

Data Index: 624241 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1011817 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7044. Min Act: -0.0000

Data Index: 805832 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7263. Min Act: -0.0000

Data Index: 967199 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7562. Min Act: -0.0000

Data Index: 670126 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7360. Min Act: -0.0000

Data Index: 1107051 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1121248 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7565. Min Act: -0.0000

Data Index: 940402 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1110089 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7202. Min Act: -0.0000

Data Index: 808982 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7145. Min Act: -0.0000

Data Index: 356292 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6843. Min Act: -0.0000

Data Index: 366266 (C4 (Web Text))

Max Activating Token Index: 432