Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3031 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.7096. Min Act: -0.0000

Data Index: 234488 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.7458. Min Act: -0.0001

Data Index: 483398 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.7178. Min Act: -0.0000

Data Index: 636389 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1190289 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.7232. Min Act: -0.0000

Data Index: 989670 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.7226. Min Act: -0.0001

Data Index: 966176 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.7030. Min Act: -0.0000

Data Index: 197087 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6595. Min Act: 0.0000

Data Index: 930321 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1354795 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6830. Min Act: -0.0001

Data Index: 57077 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6796. Min Act: -0.0000

Data Index: 598513 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6502. Min Act: -0.0000

Data Index: 490240 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6753. Min Act: -0.0001

Data Index: 249152 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6725. Min Act: -0.0000

Data Index: 483067 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6069. Min Act: -0.0001

Data Index: 918057 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6447. Min Act: -0.0000

Data Index: 1219593 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6426. Min Act: -0.0000

Data Index: 1243497 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6554. Min Act: -0.0000

Data Index: 58882 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1061585 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6391. Min Act: -0.0001

Data Index: 1140820 (C4 (Web Text))

Max Activating Token Index: 1015