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

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

Neuron 3798 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.8971. Min Act: -0.0000

Data Index: 315772 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.7423. Min Act: -0.0000

Data Index: 1539896 (Python Code)

Max Activating Token Index: 731

Text #2

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.3947. Min Act: -0.0000

Data Index: 500223 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.0162. Min Act: -0.0000

Data Index: 675796 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.6107. Min Act: -0.0000

Data Index: 726090 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.0737. Min Act: -0.0000

Data Index: 778711 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.2792. Min Act: -0.0000

Data Index: 1302800 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.0715. Min Act: -0.0000

Data Index: 774523 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 5.8971. Min Range: -5.8971

Max Act: 4.2045. Min Act: -0.0000

Data Index: 330504 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 5.8971. Min Range: -5.8971

Max Act: 4.6732. Min Act: -0.0000

Data Index: 912184 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 5.8971. Min Range: -5.8971

Max Act: 4.3133. Min Act: -0.0000

Data Index: 144462 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 5.8971. Min Range: -5.8971

Max Act: 4.3598. Min Act: -0.0000

Data Index: 723650 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 5.8971. Min Range: -5.8971

Max Act: 4.9395. Min Act: -0.0000

Data Index: 1409536 (Python Code)

Max Activating Token Index: 109

Text #13

Max Range: 5.8971. Min Range: -5.8971

Max Act: 4.4394. Min Act: -0.0000

Data Index: 1545422 (Python Code)

Max Activating Token Index: 718

Text #14

Max Range: 5.8971. Min Range: -5.8971

Max Act: 4.2758. Min Act: -0.0000

Data Index: 499890 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 5.8971. Min Range: -5.8971

Max Act: 4.6155. Min Act: -0.0000

Data Index: 859598 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 5.8971. Min Range: -5.8971

Max Act: 4.1279. Min Act: -0.0000

Data Index: 228533 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 5.8971. Min Range: -5.8971

Max Act: 4.1622. Min Act: -0.0000

Data Index: 1121902 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 5.8971. Min Range: -5.8971

Max Act: 4.1365. Min Act: -0.0000

Data Index: 1337182 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 5.8971. Min Range: -5.8971

Max Act: 4.6328. Min Act: -0.0000

Data Index: 1011573 (C4 (Web Text))

Max Activating Token Index: 28