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

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

Neuron 3222 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2973. Min Act: -0.0000

Data Index: 615108 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.3221. Min Act: -0.0000

Data Index: 338997 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.3084. Min Act: -0.0000

Data Index: 691138 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2807. Min Act: -0.0000

Data Index: 186279 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.3164. Min Act: -0.0000

Data Index: 997039 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.3058. Min Act: -0.0000

Data Index: 181275 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2813. Min Act: -0.0000

Data Index: 704209 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2963. Min Act: -0.0000

Data Index: 216570 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2825. Min Act: -0.0000

Data Index: 114836 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2836. Min Act: -0.0000

Data Index: 49595 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2941. Min Act: -0.0000

Data Index: 49045 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2576. Min Act: -0.0000

Data Index: 517771 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2750. Min Act: -0.0000

Data Index: 304176 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2690. Min Act: -0.0000

Data Index: 691807 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2529. Min Act: -0.0000

Data Index: 215153 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2594. Min Act: -0.0000

Data Index: 599181 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2597. Min Act: -0.0000

Data Index: 758248 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2356. Min Act: -0.0000

Data Index: 86369 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2440. Min Act: -0.0000

Data Index: 1268425 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2681. Min Act: -0.0000

Data Index: 471348 (C4 (Web Text))

Max Activating Token Index: 354