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

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

Neuron 1192 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: 0.5175. Min Range: -0.5175

Max Act: 0.5175. Min Act: -0.0000

Data Index: 826866 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3870. Min Act: -0.0000

Data Index: 958764 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3581. Min Act: -0.0000

Data Index: 813051 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3627. Min Act: -0.0000

Data Index: 773761 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3416. Min Act: -0.0000

Data Index: 270657 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3275. Min Act: -0.0000

Data Index: 903506 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3118. Min Act: -0.0000

Data Index: 1117786 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3304. Min Act: -0.0000

Data Index: 837531 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3062. Min Act: -0.0000

Data Index: 998805 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3054. Min Act: -0.0000

Data Index: 1148384 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.2698. Min Act: -0.0000

Data Index: 174075 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.2851. Min Act: -0.0000

Data Index: 232909 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.2674. Min Act: -0.0000

Data Index: 799050 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.2443. Min Act: -0.0000

Data Index: 610940 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1569563 (Python Code)

Max Activating Token Index: 755

Text #15

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.2356. Min Act: -0.0000

Data Index: 1057340 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.2488. Min Act: -0.0000

Data Index: 216191 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.2368. Min Act: -0.0000

Data Index: 461776 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.2478. Min Act: -0.0000

Data Index: 274133 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1349643 (C4 (Web Text))

Max Activating Token Index: 189