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

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

Neuron 3751 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.3100. Min Act: -0.0000

Data Index: 1236242 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.3082. Min Act: -0.0000

Data Index: 1117323 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2935. Min Act: -0.0000

Data Index: 771265 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1342706 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2608. Min Act: 0.0000

Data Index: 615818 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1056393 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2501. Min Act: -0.0000

Data Index: 838936 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2475. Min Act: -0.0000

Data Index: 265732 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2460. Min Act: -0.0000

Data Index: 487588 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2392. Min Act: -0.0000

Data Index: 119156 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2252. Min Act: -0.0000

Data Index: 723873 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2311. Min Act: -0.0000

Data Index: 171818 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2362. Min Act: -0.0000

Data Index: 254715 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2360. Min Act: -0.0000

Data Index: 987079 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2359. Min Act: -0.0000

Data Index: 811926 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2312. Min Act: 0.0000

Data Index: 561154 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2255. Min Act: -0.0000

Data Index: 237377 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2303. Min Act: -0.0000

Data Index: 14357 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2311. Min Act: -0.0000

Data Index: 412106 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2440. Min Act: -0.0000

Data Index: 57620 (C4 (Web Text))

Max Activating Token Index: 993