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

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

Neuron 807 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: 3.8027. Min Range: -3.8027

Max Act: 3.8027. Min Act: -0.0000

Data Index: 1205247 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 3.8027. Min Range: -3.8027

Max Act: 3.3875. Min Act: -0.0000

Data Index: 11182 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 3.8027. Min Range: -3.8027

Max Act: 3.2156. Min Act: -0.0000

Data Index: 1153469 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 3.8027. Min Range: -3.8027

Max Act: 3.0303. Min Act: -0.0000

Data Index: 1241581 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 3.8027. Min Range: -3.8027

Max Act: 3.3528. Min Act: -0.0000

Data Index: 1001424 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 3.8027. Min Range: -3.8027

Max Act: 3.1830. Min Act: -0.0000

Data Index: 1225534 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 3.8027. Min Range: -3.8027

Max Act: 3.0480. Min Act: -0.0000

Data Index: 223419 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 3.8027. Min Range: -3.8027

Max Act: 3.0377. Min Act: -0.0000

Data Index: 972510 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 3.8027. Min Range: -3.8027

Max Act: 2.9783. Min Act: -0.0000

Data Index: 878951 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 3.8027. Min Range: -3.8027

Max Act: 3.1209. Min Act: -0.0000

Data Index: 234152 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 3.8027. Min Range: -3.8027

Max Act: 2.8421. Min Act: -0.0000

Data Index: 1169126 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 3.8027. Min Range: -3.8027

Max Act: 2.7379. Min Act: -0.0000

Data Index: 742252 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 3.8027. Min Range: -3.8027

Max Act: 2.7065. Min Act: -0.0000

Data Index: 485632 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 3.8027. Min Range: -3.8027

Max Act: 2.7043. Min Act: -0.0000

Data Index: 456853 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 3.8027. Min Range: -3.8027

Max Act: 2.6839. Min Act: -0.0000

Data Index: 301400 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 3.8027. Min Range: -3.8027

Max Act: 2.4450. Min Act: -0.0000

Data Index: 182103 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 3.8027. Min Range: -3.8027

Max Act: 2.6623. Min Act: -0.0000

Data Index: 732283 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 3.8027. Min Range: -3.8027

Max Act: 2.5178. Min Act: -0.0000

Data Index: 1225727 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 3.8027. Min Range: -3.8027

Max Act: 2.6451. Min Act: -0.0000

Data Index: 703130 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 3.8027. Min Range: -3.8027

Max Act: 2.4853. Min Act: -0.0000

Data Index: 495303 (C4 (Web Text))

Max Activating Token Index: 160