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

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

Neuron 2270 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7966. Min Range: -4.7966

Max Act: 4.7966. Min Act: -0.0000

Data Index: 751613 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 4.7966. Min Range: -4.7966

Max Act: 3.2935. Min Act: -0.0000

Data Index: 1328488 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 4.7966. Min Range: -4.7966

Max Act: 2.7791. Min Act: 0.0000

Data Index: 163213 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 4.7966. Min Range: -4.7966

Max Act: 2.8684. Min Act: 0.0000

Data Index: 337239 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 4.7966. Min Range: -4.7966

Max Act: 2.6074. Min Act: -0.0000

Data Index: 335436 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 4.7966. Min Range: -4.7966

Max Act: 2.3909. Min Act: 0.0001

Data Index: 913496 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 4.7966. Min Range: -4.7966

Max Act: 2.1262. Min Act: -0.0000

Data Index: 288432 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 4.7966. Min Range: -4.7966

Max Act: 1.9927. Min Act: -0.0000

Data Index: 1434836 (Python Code)

Max Activating Token Index: 844

Text #8

Max Range: 4.7966. Min Range: -4.7966

Max Act: 2.2973. Min Act: -0.0000

Data Index: 1092722 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 4.7966. Min Range: -4.7966

Max Act: 2.0826. Min Act: -0.0000

Data Index: 703668 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 4.7966. Min Range: -4.7966

Max Act: 1.8172. Min Act: -0.0000

Data Index: 865852 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 4.7966. Min Range: -4.7966

Max Act: 1.7447. Min Act: 0.0000

Data Index: 766245 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 4.7966. Min Range: -4.7966

Max Act: 1.7813. Min Act: -0.0000

Data Index: 258825 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 4.7966. Min Range: -4.7966

Max Act: 1.3582. Min Act: -0.0000

Data Index: 64710 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 4.7966. Min Range: -4.7966

Max Act: 1.8331. Min Act: -0.0000

Data Index: 891677 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 4.7966. Min Range: -4.7966

Max Act: 1.9349. Min Act: -0.0000

Data Index: 680447 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 4.7966. Min Range: -4.7966

Max Act: 1.7227. Min Act: -0.0000

Data Index: 824630 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 4.7966. Min Range: -4.7966

Max Act: 1.7176. Min Act: -0.0000

Data Index: 617164 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 4.7966. Min Range: -4.7966

Max Act: 1.6087. Min Act: -0.0000

Data Index: 154550 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 4.7966. Min Range: -4.7966

Max Act: 1.6982. Min Act: -0.0000

Data Index: 1233599 (C4 (Web Text))

Max Activating Token Index: 944