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

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

Neuron 5712 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.4500. Min Act: 0.0002

Data Index: 497163 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.4315. Min Act: 0.0001

Data Index: 1309086 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.4088. Min Act: -0.0000

Data Index: 1012173 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.4114. Min Act: -0.0000

Data Index: 55154 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3663. Min Act: -0.0000

Data Index: 563406 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3644. Min Act: -0.0000

Data Index: 188759 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3604. Min Act: -0.0000

Data Index: 823454 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3587. Min Act: -0.0000

Data Index: 244631 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3599. Min Act: -0.0000

Data Index: 11912 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3595. Min Act: -0.0000

Data Index: 886228 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3261. Min Act: -0.0000

Data Index: 35446 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3469. Min Act: 0.0002

Data Index: 1229872 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3234. Min Act: -0.0000

Data Index: 778729 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3440. Min Act: -0.0000

Data Index: 820881 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1579930 (Python Code)

Max Activating Token Index: 748

Text #15

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3180. Min Act: -0.0000

Data Index: 799820 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3440. Min Act: 0.0000

Data Index: 1338141 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1192786 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3087. Min Act: -0.0000

Data Index: 973909 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3398. Min Act: -0.0000

Data Index: 765650 (C4 (Web Text))

Max Activating Token Index: 30