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

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

Neuron 3041 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6994. Min Range: -2.6994

Max Act: 2.6994. Min Act: -0.0001

Data Index: 359795 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 2.6994. Min Range: -2.6994

Max Act: 2.5775. Min Act: -0.0000

Data Index: 628366 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 2.6994. Min Range: -2.6994

Max Act: 2.4614. Min Act: -0.0000

Data Index: 333239 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 2.6994. Min Range: -2.6994

Max Act: 2.1960. Min Act: -0.0000

Data Index: 873758 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 2.6994. Min Range: -2.6994

Max Act: 2.3974. Min Act: -0.0001

Data Index: 679437 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 2.6994. Min Range: -2.6994

Max Act: 2.2700. Min Act: -0.0001

Data Index: 1195851 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 2.6994. Min Range: -2.6994

Max Act: 2.2080. Min Act: -0.0001

Data Index: 283515 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 2.6994. Min Range: -2.6994

Max Act: 2.1875. Min Act: -0.0000

Data Index: 338798 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 2.6994. Min Range: -2.6994

Max Act: 2.1532. Min Act: -0.0000

Data Index: 699973 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 2.6994. Min Range: -2.6994

Max Act: 2.1286. Min Act: -0.0000

Data Index: 268766 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 2.6994. Min Range: -2.6994

Max Act: 2.0164. Min Act: -0.0000

Data Index: 304944 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 2.6994. Min Range: -2.6994

Max Act: 2.1295. Min Act: -0.0001

Data Index: 247314 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 2.6994. Min Range: -2.6994

Max Act: 1.9558. Min Act: -0.0001

Data Index: 279283 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 2.6994. Min Range: -2.6994

Max Act: 2.0386. Min Act: -0.0000

Data Index: 214649 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 2.6994. Min Range: -2.6994

Max Act: 2.0228. Min Act: -0.0000

Data Index: 723408 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 2.6994. Min Range: -2.6994

Max Act: 2.0221. Min Act: -0.0000

Data Index: 1062813 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 2.6994. Min Range: -2.6994

Max Act: 1.9703. Min Act: -0.0000

Data Index: 715727 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 2.6994. Min Range: -2.6994

Max Act: 2.1038. Min Act: -0.0000

Data Index: 1163532 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 2.6994. Min Range: -2.6994

Max Act: 1.9554. Min Act: -0.0000

Data Index: 410323 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 2.6994. Min Range: -2.6994

Max Act: 1.9814. Min Act: -0.0000

Data Index: 1134321 (C4 (Web Text))

Max Activating Token Index: 428