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

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

Neuron 468 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5114. Min Range: -2.5114

Max Act: 2.5114. Min Act: -0.0000

Data Index: 153032 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 2.5114. Min Range: -2.5114

Max Act: 1.8848. Min Act: -0.0000

Data Index: 228033 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 2.5114. Min Range: -2.5114

Max Act: 1.7153. Min Act: -0.0000

Data Index: 353099 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 2.5114. Min Range: -2.5114

Max Act: 1.5917. Min Act: -0.0000

Data Index: 288663 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 2.5114. Min Range: -2.5114

Max Act: 1.5757. Min Act: -0.0000

Data Index: 1236882 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 2.5114. Min Range: -2.5114

Max Act: 1.5295. Min Act: -0.0000

Data Index: 676788 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 2.5114. Min Range: -2.5114

Max Act: 1.6257. Min Act: -0.0000

Data Index: 303375 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 2.5114. Min Range: -2.5114

Max Act: 1.4456. Min Act: -0.0000

Data Index: 1233047 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 2.5114. Min Range: -2.5114

Max Act: 1.5394. Min Act: -0.0000

Data Index: 1149430 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 2.5114. Min Range: -2.5114

Max Act: 1.4415. Min Act: -0.0000

Data Index: 827878 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 2.5114. Min Range: -2.5114

Max Act: 1.5075. Min Act: -0.0000

Data Index: 587140 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 2.5114. Min Range: -2.5114

Max Act: 1.4290. Min Act: -0.0000

Data Index: 184302 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 2.5114. Min Range: -2.5114

Max Act: 1.4078. Min Act: -0.0000

Data Index: 110026 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 2.5114. Min Range: -2.5114

Max Act: 1.3702. Min Act: -0.0000

Data Index: 685745 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 2.5114. Min Range: -2.5114

Max Act: 1.3763. Min Act: -0.0000

Data Index: 1339699 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 2.5114. Min Range: -2.5114

Max Act: 1.3409. Min Act: -0.0000

Data Index: 406282 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 2.5114. Min Range: -2.5114

Max Act: 1.3267. Min Act: -0.0000

Data Index: 1165351 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 2.5114. Min Range: -2.5114

Max Act: 1.2873. Min Act: -0.0000

Data Index: 989948 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 2.5114. Min Range: -2.5114

Max Act: 1.2899. Min Act: -0.0000

Data Index: 3208 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 2.5114. Min Range: -2.5114

Max Act: 1.2052. Min Act: -0.0000

Data Index: 504606 (C4 (Web Text))

Max Activating Token Index: 463