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

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

Neuron 4076 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4941. Min Act: -0.0003

Data Index: 207689 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4558. Min Act: -0.0003

Data Index: 787965 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3926. Min Act: -0.0003

Data Index: 1131020 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3628. Min Act: -0.0003

Data Index: 499968 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3623. Min Act: -0.0003

Data Index: 310667 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3569. Min Act: -0.0002

Data Index: 1214736 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3669. Min Act: -0.0003

Data Index: 772056 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3503. Min Act: -0.0003

Data Index: 1221295 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3511. Min Act: -0.0003

Data Index: 1259503 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3479. Min Act: -0.0003

Data Index: 86097 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3399. Min Act: -0.0003

Data Index: 1252267 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3373. Min Act: -0.0003

Data Index: 99325 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3344. Min Act: -0.0003

Data Index: 352442 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3354. Min Act: -0.0003

Data Index: 1248661 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3358. Min Act: -0.0003

Data Index: 1065941 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3347. Min Act: -0.0003

Data Index: 1321712 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3276. Min Act: -0.0003

Data Index: 925370 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3256. Min Act: -0.0003

Data Index: 24485 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3080. Min Act: -0.0003

Data Index: 801309 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3197. Min Act: -0.0003

Data Index: 1013952 (C4 (Web Text))

Max Activating Token Index: 651