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

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

Neuron 64 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2817. Min Range: -2.2817

Max Act: 2.2817. Min Act: -0.0000

Data Index: 719912 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 2.2817. Min Range: -2.2817

Max Act: 2.0418. Min Act: -0.0000

Data Index: 853068 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 2.2817. Min Range: -2.2817

Max Act: 2.1651. Min Act: -0.0000

Data Index: 937429 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 2.2817. Min Range: -2.2817

Max Act: 1.9586. Min Act: -0.0000

Data Index: 1308760 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 2.2817. Min Range: -2.2817

Max Act: 1.9379. Min Act: -0.0000

Data Index: 1096723 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 2.2817. Min Range: -2.2817

Max Act: 1.7347. Min Act: -0.0000

Data Index: 1260412 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 2.2817. Min Range: -2.2817

Max Act: 1.8815. Min Act: -0.0000

Data Index: 603734 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 2.2817. Min Range: -2.2817

Max Act: 1.9603. Min Act: -0.0000

Data Index: 93326 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 2.2817. Min Range: -2.2817

Max Act: 1.8629. Min Act: -0.0000

Data Index: 315747 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 2.2817. Min Range: -2.2817

Max Act: 1.7549. Min Act: -0.0000

Data Index: 45460 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 2.2817. Min Range: -2.2817

Max Act: 1.7920. Min Act: -0.0000

Data Index: 222996 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 2.2817. Min Range: -2.2817

Max Act: 1.7376. Min Act: -0.0000

Data Index: 1189002 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 2.2817. Min Range: -2.2817

Max Act: 1.9244. Min Act: -0.0000

Data Index: 9790 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 2.2817. Min Range: -2.2817

Max Act: 1.8221. Min Act: -0.0000

Data Index: 657504 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 2.2817. Min Range: -2.2817

Max Act: 1.8207. Min Act: -0.0000

Data Index: 996877 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 2.2817. Min Range: -2.2817

Max Act: 1.8050. Min Act: -0.0000

Data Index: 122076 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 2.2817. Min Range: -2.2817

Max Act: 1.6996. Min Act: -0.0000

Data Index: 390010 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 2.2817. Min Range: -2.2817

Max Act: 1.7672. Min Act: -0.0000

Data Index: 154661 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 2.2817. Min Range: -2.2817

Max Act: 1.7555. Min Act: -0.0000

Data Index: 1070951 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 2.2817. Min Range: -2.2817

Max Act: 1.6374. Min Act: -0.0000

Data Index: 270621 (C4 (Web Text))

Max Activating Token Index: 218