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

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

Neuron 4294 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2966. Min Range: -3.2966

Max Act: 3.2966. Min Act: -0.0000

Data Index: 1050104 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 3.2966. Min Range: -3.2966

Max Act: 3.2162. Min Act: -0.0000

Data Index: 704235 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 3.2966. Min Range: -3.2966

Max Act: 3.0412. Min Act: -0.0000

Data Index: 922470 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 3.2966. Min Range: -3.2966

Max Act: 3.1596. Min Act: -0.0000

Data Index: 273923 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 3.2966. Min Range: -3.2966

Max Act: 3.0441. Min Act: -0.0000

Data Index: 383654 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 3.2966. Min Range: -3.2966

Max Act: 2.9875. Min Act: -0.0000

Data Index: 872665 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 3.2966. Min Range: -3.2966

Max Act: 2.8258. Min Act: -0.0000

Data Index: 883657 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 3.2966. Min Range: -3.2966

Max Act: 2.9481. Min Act: -0.0000

Data Index: 175535 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 3.2966. Min Range: -3.2966

Max Act: 2.9160. Min Act: -0.0000

Data Index: 406386 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 3.2966. Min Range: -3.2966

Max Act: 2.9323. Min Act: -0.0000

Data Index: 920997 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 3.2966. Min Range: -3.2966

Max Act: 2.9360. Min Act: -0.0000

Data Index: 77950 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 3.2966. Min Range: -3.2966

Max Act: 2.9017. Min Act: -0.0000

Data Index: 489063 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 3.2966. Min Range: -3.2966

Max Act: 3.0311. Min Act: -0.0000

Data Index: 125652 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 3.2966. Min Range: -3.2966

Max Act: 2.8859. Min Act: -0.0000

Data Index: 129383 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 3.2966. Min Range: -3.2966

Max Act: 2.7654. Min Act: -0.0000

Data Index: 952163 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 3.2966. Min Range: -3.2966

Max Act: 2.8612. Min Act: -0.0000

Data Index: 294459 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 3.2966. Min Range: -3.2966

Max Act: 3.0937. Min Act: -0.0000

Data Index: 273589 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 3.2966. Min Range: -3.2966

Max Act: 2.7855. Min Act: -0.0000

Data Index: 389923 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 3.2966. Min Range: -3.2966

Max Act: 2.7156. Min Act: -0.0000

Data Index: 525656 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 3.2966. Min Range: -3.2966

Max Act: 2.7099. Min Act: -0.0000

Data Index: 68687 (C4 (Web Text))

Max Activating Token Index: 214