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

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

Neuron 4318 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6208. Min Range: -2.6208

Max Act: 2.6208. Min Act: -0.0000

Data Index: 570899 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 2.6208. Min Range: -2.6208

Max Act: 2.4307. Min Act: -0.0000

Data Index: 1045641 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 2.6208. Min Range: -2.6208

Max Act: 2.3953. Min Act: -0.0000

Data Index: 1352244 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 2.6208. Min Range: -2.6208

Max Act: 2.2178. Min Act: -0.0000

Data Index: 1000318 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 2.6208. Min Range: -2.6208

Max Act: 2.1463. Min Act: -0.0000

Data Index: 71362 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 2.6208. Min Range: -2.6208

Max Act: 2.1876. Min Act: -0.0000

Data Index: 1290022 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 2.6208. Min Range: -2.6208

Max Act: 2.1598. Min Act: -0.0000

Data Index: 1080584 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 2.6208. Min Range: -2.6208

Max Act: 2.2489. Min Act: -0.0000

Data Index: 1245085 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 2.6208. Min Range: -2.6208

Max Act: 2.1026. Min Act: -0.0000

Data Index: 577170 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 2.6208. Min Range: -2.6208

Max Act: 1.9673. Min Act: -0.0000

Data Index: 136757 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 2.6208. Min Range: -2.6208

Max Act: 2.0481. Min Act: -0.0000

Data Index: 1523889 (Python Code)

Max Activating Token Index: 808

Text #11

Max Range: 2.6208. Min Range: -2.6208

Max Act: 1.9174. Min Act: -0.0000

Data Index: 1338016 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 2.6208. Min Range: -2.6208

Max Act: 2.0273. Min Act: -0.0000

Data Index: 1234691 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 2.6208. Min Range: -2.6208

Max Act: 1.8877. Min Act: -0.0000

Data Index: 1084324 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 2.6208. Min Range: -2.6208

Max Act: 1.8771. Min Act: -0.0000

Data Index: 554157 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 2.6208. Min Range: -2.6208

Max Act: 2.0533. Min Act: -0.0000

Data Index: 821146 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 2.6208. Min Range: -2.6208

Max Act: 1.8210. Min Act: -0.0000

Data Index: 467845 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 2.6208. Min Range: -2.6208

Max Act: 2.0267. Min Act: -0.0000

Data Index: 1522004 (Python Code)

Max Activating Token Index: 879

Text #18

Max Range: 2.6208. Min Range: -2.6208

Max Act: 1.9105. Min Act: -0.0000

Data Index: 1071886 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 2.6208. Min Range: -2.6208

Max Act: 1.8049. Min Act: -0.0000

Data Index: 1460324 (Python Code)

Max Activating Token Index: 372