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

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

Neuron 3625 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5155. Min Range: -6.5155

Max Act: 6.5155. Min Act: -0.0000

Data Index: 16511 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 6.5155. Min Range: -6.5155

Max Act: 5.5780. Min Act: -0.0000

Data Index: 751851 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 6.5155. Min Range: -6.5155

Max Act: 5.6392. Min Act: -0.0000

Data Index: 1121525 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 6.5155. Min Range: -6.5155

Max Act: 5.5114. Min Act: -0.0000

Data Index: 549376 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 6.5155. Min Range: -6.5155

Max Act: 5.6045. Min Act: -0.0000

Data Index: 422529 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 6.5155. Min Range: -6.5155

Max Act: 5.1749. Min Act: -0.0000

Data Index: 928315 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 6.5155. Min Range: -6.5155

Max Act: 5.0366. Min Act: -0.0000

Data Index: 84813 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 6.5155. Min Range: -6.5155

Max Act: 5.1960. Min Act: -0.0000

Data Index: 840365 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 6.5155. Min Range: -6.5155

Max Act: 5.1632. Min Act: -0.0000

Data Index: 1235598 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 6.5155. Min Range: -6.5155

Max Act: 5.3120. Min Act: -0.0000

Data Index: 667576 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 6.5155. Min Range: -6.5155

Max Act: 5.2710. Min Act: -0.0000

Data Index: 425345 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 6.5155. Min Range: -6.5155

Max Act: 5.0700. Min Act: -0.0000

Data Index: 716573 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 6.5155. Min Range: -6.5155

Max Act: 5.0553. Min Act: -0.0000

Data Index: 928657 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 6.5155. Min Range: -6.5155

Max Act: 5.0106. Min Act: -0.0000

Data Index: 351522 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 6.5155. Min Range: -6.5155

Max Act: 4.5590. Min Act: -0.0000

Data Index: 496086 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 6.5155. Min Range: -6.5155

Max Act: 4.5908. Min Act: -0.0000

Data Index: 1275003 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 6.5155. Min Range: -6.5155

Max Act: 4.4777. Min Act: -0.0000

Data Index: 250668 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 6.5155. Min Range: -6.5155

Max Act: 4.7631. Min Act: -0.0000

Data Index: 58188 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 6.5155. Min Range: -6.5155

Max Act: 4.5058. Min Act: -0.0000

Data Index: 999890 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 6.5155. Min Range: -6.5155

Max Act: 4.6695. Min Act: -0.0000

Data Index: 1343649 (C4 (Web Text))

Max Activating Token Index: 175