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

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

Neuron 4635 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.8603. Min Act: 0.0000

Data Index: 504883 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.5025. Min Act: -0.0000

Data Index: 1344783 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.5323. Min Act: -0.0000

Data Index: 911434 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.5626. Min Act: -0.0000

Data Index: 809609 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.5645. Min Act: -0.0000

Data Index: 460394 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.4867. Min Act: -0.0000

Data Index: 791711 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.5383. Min Act: -0.0000

Data Index: 6243 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.3339. Min Act: -0.0000

Data Index: 1345378 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.2832. Min Act: -0.0000

Data Index: 1104321 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.4301. Min Act: -0.0000

Data Index: 946257 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.3152. Min Act: -0.0000

Data Index: 62386 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.2989. Min Act: -0.0000

Data Index: 900720 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.2257. Min Act: -0.0000

Data Index: 222738 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.2929. Min Act: -0.0000

Data Index: 356260 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.2080. Min Act: -0.0000

Data Index: 191044 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.2545. Min Act: -0.0000

Data Index: 102982 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.2449. Min Act: -0.0000

Data Index: 240811 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.2353. Min Act: -0.0000

Data Index: 166579 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.2374. Min Act: -0.0000

Data Index: 845332 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.3178. Min Act: -0.0000

Data Index: 84811 (C4 (Web Text))

Max Activating Token Index: 866