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

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

Neuron 18 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: 0.5332. Min Range: -0.5332

Max Act: 0.5329. Min Act: -0.0000

Data Index: 825056 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.5332. Min Act: -0.0000

Data Index: 173031 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.5147. Min Act: -0.0000

Data Index: 756230 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.4532. Min Act: -0.0000

Data Index: 788864 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.4681. Min Act: -0.0000

Data Index: 33718 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.4572. Min Act: -0.0000

Data Index: 283148 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.4415. Min Act: -0.0000

Data Index: 54715 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.4282. Min Act: -0.0000

Data Index: 24075 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.4027. Min Act: -0.0000

Data Index: 285189 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.4160. Min Act: -0.0000

Data Index: 1210033 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.4023. Min Act: -0.0000

Data Index: 190503 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3967. Min Act: -0.0000

Data Index: 105473 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1119001 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3658. Min Act: -0.0000

Data Index: 744463 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3603. Min Act: -0.0000

Data Index: 312993 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3884. Min Act: -0.0000

Data Index: 483512 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.4105. Min Act: -0.0000

Data Index: 1194642 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3586. Min Act: -0.0000

Data Index: 192529 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3830. Min Act: -0.0000

Data Index: 876022 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3676. Min Act: -0.0000

Data Index: 500469 (C4 (Web Text))

Max Activating Token Index: 44