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

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

Neuron 4877 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: 0.8320. Min Range: -0.8320

Max Act: 0.8320. Min Act: -0.0000

Data Index: 158754 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7533. Min Act: -0.0000

Data Index: 791584 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7372. Min Act: -0.0000

Data Index: 180372 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6928. Min Act: -0.0000

Data Index: 480090 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6177. Min Act: -0.0000

Data Index: 910545 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6150. Min Act: -0.0000

Data Index: 135464 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6029. Min Act: -0.0000

Data Index: 617486 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6278. Min Act: -0.0000

Data Index: 731535 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6279. Min Act: -0.0000

Data Index: 402465 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1053810 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5645. Min Act: -0.0000

Data Index: 288722 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5851. Min Act: -0.0000

Data Index: 734450 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5536. Min Act: -0.0000

Data Index: 729461 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5381. Min Act: -0.0000

Data Index: 1306161 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5274. Min Act: -0.0000

Data Index: 912891 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1081851 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5336. Min Act: -0.0000

Data Index: 684772 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5483. Min Act: -0.0000

Data Index: 945434 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5046. Min Act: -0.0000

Data Index: 481864 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1316475 (C4 (Web Text))

Max Activating Token Index: 597