Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 77 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.4225. Min Act: -0.0000

Data Index: 707338 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.4253. Min Act: -0.0001

Data Index: 963017 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.4108. Min Act: -0.0001

Data Index: 1290961 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.4015. Min Act: -0.0001

Data Index: 598651 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1327044 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.3756. Min Act: -0.0000

Data Index: 834747 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.3586. Min Act: -0.0001

Data Index: 807185 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.3676. Min Act: -0.0001

Data Index: 271678 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.3556. Min Act: -0.0000

Data Index: 239955 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.3749. Min Act: -0.0001

Data Index: 56337 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.3386. Min Act: -0.0001

Data Index: 276864 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.3488. Min Act: -0.0001

Data Index: 712570 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.3361. Min Act: -0.0001

Data Index: 946294 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.3323. Min Act: -0.0000

Data Index: 1340987 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.3410. Min Act: -0.0001

Data Index: 1268565 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.3355. Min Act: -0.0001

Data Index: 1289032 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.3373. Min Act: -0.0001

Data Index: 230343 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.3411. Min Act: -0.0001

Data Index: 776862 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.3178. Min Act: -0.0001

Data Index: 1304170 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.4253. Min Range: -0.4253

Max Act: 0.3166. Min Act: -0.0000

Data Index: 96274 (C4 (Web Text))

Max Activating Token Index: 646