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

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

Neuron 2422 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3231. Min Range: -1.3231

Max Act: 1.3231. Min Act: -0.0000

Data Index: 1105553 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 1.3231. Min Range: -1.3231

Max Act: 1.0176. Min Act: -0.0000

Data Index: 474546 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 1.3231. Min Range: -1.3231

Max Act: 0.8666. Min Act: -0.0000

Data Index: 388761 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 1.3231. Min Range: -1.3231

Max Act: 0.8541. Min Act: -0.0000

Data Index: 896688 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 1.3231. Min Range: -1.3231

Max Act: 0.7888. Min Act: -0.0000

Data Index: 1109398 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 1.3231. Min Range: -1.3231

Max Act: 0.8129. Min Act: -0.0000

Data Index: 354024 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 1.3231. Min Range: -1.3231

Max Act: 0.7639. Min Act: -0.0000

Data Index: 107588 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 1.3231. Min Range: -1.3231

Max Act: 0.7951. Min Act: -0.0000

Data Index: 821211 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 1.3231. Min Range: -1.3231

Max Act: 0.7473. Min Act: -0.0000

Data Index: 982242 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 1.3231. Min Range: -1.3231

Max Act: 0.7372. Min Act: -0.0000

Data Index: 326749 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 1.3231. Min Range: -1.3231

Max Act: 0.6972. Min Act: -0.0000

Data Index: 1159299 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 1.3231. Min Range: -1.3231

Max Act: 0.6877. Min Act: -0.0000

Data Index: 534216 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 1.3231. Min Range: -1.3231

Max Act: 0.7250. Min Act: -0.0000

Data Index: 906665 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 1.3231. Min Range: -1.3231

Max Act: 0.6964. Min Act: -0.0000

Data Index: 622866 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 1.3231. Min Range: -1.3231

Max Act: 0.6900. Min Act: -0.0000

Data Index: 393263 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 1.3231. Min Range: -1.3231

Max Act: 0.6912. Min Act: -0.0000

Data Index: 184486 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 1.3231. Min Range: -1.3231

Max Act: 0.7009. Min Act: -0.0000

Data Index: 1001935 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 1.3231. Min Range: -1.3231

Max Act: 0.6659. Min Act: -0.0000

Data Index: 475878 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 1.3231. Min Range: -1.3231

Max Act: 0.6374. Min Act: -0.0000

Data Index: 766321 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 1.3231. Min Range: -1.3231

Max Act: 0.5991. Min Act: -0.0000

Data Index: 249263 (C4 (Web Text))

Max Activating Token Index: 1011