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

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

Neuron 1406 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: 0.6252. Min Range: -0.6252

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1207636 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.4551. Min Act: -0.0000

Data Index: 1097259 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1406840 (Python Code)

Max Activating Token Index: 811

Text #3

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3737. Min Act: -0.0000

Data Index: 974300 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3897. Min Act: -0.0000

Data Index: 162497 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3299. Min Act: 0.0000

Data Index: 1562385 (Python Code)

Max Activating Token Index: 131

Text #6

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3721. Min Act: -0.0000

Data Index: 227694 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1603622 (Python Code)

Max Activating Token Index: 269

Text #8

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3563. Min Act: -0.0000

Data Index: 931990 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3110. Min Act: -0.0000

Data Index: 752886 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1385545 (Python Code)

Max Activating Token Index: 677

Text #11

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3279. Min Act: -0.0000

Data Index: 372073 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3192. Min Act: -0.0000

Data Index: 761357 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3227. Min Act: -0.0000

Data Index: 1131249 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.2821. Min Act: -0.0000

Data Index: 915999 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1109927 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3020. Min Act: 0.0000

Data Index: 1640997 (Python Code)

Max Activating Token Index: 364

Text #17

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.2943. Min Act: -0.0000

Data Index: 169355 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1620343 (Python Code)

Max Activating Token Index: 481

Text #19

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.2953. Min Act: -0.0000

Data Index: 447198 (C4 (Web Text))

Max Activating Token Index: 162