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

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

Neuron 3224 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.5215. Min Act: -0.0000

Data Index: 452862 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.4254. Min Act: -0.0000

Data Index: 247875 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1275272 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.4106. Min Act: -0.0000

Data Index: 227809 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.4074. Min Act: -0.0000

Data Index: 282015 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3934. Min Act: -0.0000

Data Index: 414911 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3888. Min Act: -0.0000

Data Index: 966716 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3769. Min Act: -0.0000

Data Index: 447114 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3726. Min Act: -0.0000

Data Index: 1256121 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3752. Min Act: -0.0000

Data Index: 234498 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3440. Min Act: -0.0000

Data Index: 403481 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3322. Min Act: -0.0000

Data Index: 133695 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3265. Min Act: -0.0000

Data Index: 776493 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3632. Min Act: -0.0000

Data Index: 554214 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3389. Min Act: -0.0000

Data Index: 361031 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3140. Min Act: -0.0000

Data Index: 395399 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1139562 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3189. Min Act: -0.0000

Data Index: 480300 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3159. Min Act: -0.0000

Data Index: 313294 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.5215. Min Range: -0.5215

Max Act: 0.3234. Min Act: -0.0000

Data Index: 1319746 (C4 (Web Text))

Max Activating Token Index: 723