Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1572 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1192065 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.8101. Min Act: -0.0000

Data Index: 804997 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7847. Min Act: -0.0000

Data Index: 665762 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7239. Min Act: -0.0000

Data Index: 691240 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6621. Min Act: -0.0000

Data Index: 187446 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6625. Min Act: -0.0000

Data Index: 1092404 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6209. Min Act: -0.0000

Data Index: 401124 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6628. Min Act: -0.0000

Data Index: 174255 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6309. Min Act: -0.0000

Data Index: 1128377 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6175. Min Act: -0.0000

Data Index: 409369 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5783. Min Act: -0.0000

Data Index: 198059 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5746. Min Act: -0.0000

Data Index: 1256788 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5711. Min Act: -0.0000

Data Index: 542084 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5719. Min Act: -0.0000

Data Index: 1180405 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5680. Min Act: -0.0000

Data Index: 1122426 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5731. Min Act: -0.0000

Data Index: 1023602 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5695. Min Act: -0.0000

Data Index: 509579 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5090. Min Act: -0.0000

Data Index: 987682 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5659. Min Act: -0.0000

Data Index: 998980 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5441. Min Act: -0.0000

Data Index: 332458 (C4 (Web Text))

Max Activating Token Index: 42