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

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

Neuron 1607 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3074. Min Range: -6.3074

Max Act: 5.6922. Min Act: -0.0000

Data Index: 540605 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 6.3074. Min Range: -6.3074

Max Act: 6.3074. Min Act: -0.0000

Data Index: 310932 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 6.3074. Min Range: -6.3074

Max Act: 5.1537. Min Act: -0.0000

Data Index: 172182 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 6.3074. Min Range: -6.3074

Max Act: 5.3371. Min Act: -0.0000

Data Index: 1324167 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 6.3074. Min Range: -6.3074

Max Act: 5.3287. Min Act: -0.0000

Data Index: 998257 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 6.3074. Min Range: -6.3074

Max Act: 4.9821. Min Act: -0.0000

Data Index: 840931 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 6.3074. Min Range: -6.3074

Max Act: 5.3172. Min Act: -0.0000

Data Index: 680255 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 6.3074. Min Range: -6.3074

Max Act: 4.7966. Min Act: -0.0000

Data Index: 381769 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 6.3074. Min Range: -6.3074

Max Act: 4.9303. Min Act: -0.0000

Data Index: 12291 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 6.3074. Min Range: -6.3074

Max Act: 5.0500. Min Act: -0.0000

Data Index: 329679 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 6.3074. Min Range: -6.3074

Max Act: 5.0236. Min Act: -0.0000

Data Index: 189634 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 6.3074. Min Range: -6.3074

Max Act: 4.9693. Min Act: -0.0000

Data Index: 116415 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 6.3074. Min Range: -6.3074

Max Act: 4.8832. Min Act: -0.0000

Data Index: 234520 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 6.3074. Min Range: -6.3074

Max Act: 4.4551. Min Act: -0.0000

Data Index: 921326 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 6.3074. Min Range: -6.3074

Max Act: 4.6234. Min Act: -0.0000

Data Index: 283437 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 6.3074. Min Range: -6.3074

Max Act: 4.7736. Min Act: -0.0000

Data Index: 366530 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 6.3074. Min Range: -6.3074

Max Act: 4.7494. Min Act: -0.0000

Data Index: 1068304 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 6.3074. Min Range: -6.3074

Max Act: 4.7218. Min Act: -0.0000

Data Index: 907036 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 6.3074. Min Range: -6.3074

Max Act: 4.7264. Min Act: -0.0000

Data Index: 732256 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 6.3074. Min Range: -6.3074

Max Act: 4.8700. Min Act: -0.0000

Data Index: 1247090 (C4 (Web Text))

Max Activating Token Index: 472