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

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

Neuron 496 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: 0.7449. Min Range: -0.7449

Max Act: 0.6836. Min Act: -0.0000

Data Index: 5519 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.7449. Min Act: -0.0000

Data Index: 718673 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.7232. Min Act: -0.0000

Data Index: 438423 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1082393 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.6483. Min Act: -0.0000

Data Index: 127196 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5743. Min Act: -0.0000

Data Index: 747335 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5735. Min Act: -0.0000

Data Index: 1271051 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.6031. Min Act: -0.0000

Data Index: 199659 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.6226. Min Act: -0.0000

Data Index: 973448 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5852. Min Act: -0.0000

Data Index: 485590 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5642. Min Act: -0.0000

Data Index: 100676 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5392. Min Act: -0.0000

Data Index: 434155 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1475004 (Python Code)

Max Activating Token Index: 185

Text #13

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5647. Min Act: -0.0000

Data Index: 699139 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5898. Min Act: -0.0000

Data Index: 529349 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5751. Min Act: -0.0000

Data Index: 578175 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5479. Min Act: -0.0000

Data Index: 966228 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1017587 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5178. Min Act: -0.0000

Data Index: 736133 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.7449. Min Range: -0.7449

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1597128 (Python Code)

Max Activating Token Index: 232