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

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

Neuron 1710 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.6688. Min Range: -6.6688

Max Act: 6.6688. Min Act: -0.0000

Data Index: 666967 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 6.6688. Min Range: -6.6688

Max Act: 5.8340. Min Act: -0.0000

Data Index: 789069 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 6.6688. Min Range: -6.6688

Max Act: 5.6946. Min Act: -0.0000

Data Index: 1049518 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 6.6688. Min Range: -6.6688

Max Act: 5.9088. Min Act: -0.0000

Data Index: 139541 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 6.6688. Min Range: -6.6688

Max Act: 5.4943. Min Act: -0.0000

Data Index: 552068 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 6.6688. Min Range: -6.6688

Max Act: 5.6235. Min Act: -0.0000

Data Index: 574991 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 6.6688. Min Range: -6.6688

Max Act: 5.6591. Min Act: -0.0000

Data Index: 831290 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 6.6688. Min Range: -6.6688

Max Act: 5.4273. Min Act: -0.0000

Data Index: 865052 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 6.6688. Min Range: -6.6688

Max Act: 5.5473. Min Act: -0.0000

Data Index: 827620 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 6.6688. Min Range: -6.6688

Max Act: 5.5195. Min Act: -0.0000

Data Index: 965500 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 6.6688. Min Range: -6.6688

Max Act: 5.1469. Min Act: -0.0000

Data Index: 358953 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 6.6688. Min Range: -6.6688

Max Act: 4.7865. Min Act: -0.0000

Data Index: 106939 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 6.6688. Min Range: -6.6688

Max Act: 5.5064. Min Act: -0.0000

Data Index: 198463 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 6.6688. Min Range: -6.6688

Max Act: 5.3221. Min Act: -0.0000

Data Index: 482027 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 6.6688. Min Range: -6.6688

Max Act: 5.2054. Min Act: -0.0000

Data Index: 972340 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 6.6688. Min Range: -6.6688

Max Act: 4.9915. Min Act: -0.0000

Data Index: 247367 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 6.6688. Min Range: -6.6688

Max Act: 5.0133. Min Act: -0.0000

Data Index: 717724 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 6.6688. Min Range: -6.6688

Max Act: 5.1752. Min Act: -0.0000

Data Index: 913076 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 6.6688. Min Range: -6.6688

Max Act: 5.2986. Min Act: -0.0000

Data Index: 265555 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 6.6688. Min Range: -6.6688

Max Act: 4.7283. Min Act: -0.0000

Data Index: 288603 (C4 (Web Text))

Max Activating Token Index: 650