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

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

Neuron 506 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: 0.4484. Min Range: -0.4484

Max Act: 0.4484. Min Act: -0.0000

Data Index: 92031 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4028. Min Act: -0.0000

Data Index: 86198 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3677. Min Act: -0.0000

Data Index: 188921 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3788. Min Act: -0.0000

Data Index: 561901 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3712. Min Act: 0.0000

Data Index: 404992 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3664. Min Act: -0.0000

Data Index: 1023216 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3409. Min Act: -0.0000

Data Index: 412906 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3612. Min Act: -0.0000

Data Index: 391148 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3556. Min Act: -0.0000

Data Index: 943942 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3650. Min Act: -0.0000

Data Index: 618427 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3538. Min Act: -0.0000

Data Index: 141481 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3476. Min Act: -0.0000

Data Index: 1147534 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3561. Min Act: -0.0000

Data Index: 368334 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3428. Min Act: 0.0000

Data Index: 1216495 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3441. Min Act: -0.0000

Data Index: 270016 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3546. Min Act: -0.0000

Data Index: 273741 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3247. Min Act: -0.0000

Data Index: 183208 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3242. Min Act: 0.0000

Data Index: 974320 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3348. Min Act: -0.0000

Data Index: 1095323 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3219. Min Act: -0.0000

Data Index: 491832 (C4 (Web Text))

Max Activating Token Index: 937