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

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

Neuron 4185 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.3306. Min Act: -0.0000

Data Index: 198501 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.2538. Min Act: -0.0000

Data Index: 455493 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.1921. Min Act: -0.0000

Data Index: 686255 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.2076. Min Act: -0.0000

Data Index: 187542 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.0378. Min Act: -0.0000

Data Index: 953208 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.0203. Min Act: -0.0000

Data Index: 1026870 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 2.3306. Min Range: -2.3306

Max Act: 1.9959. Min Act: -0.0000

Data Index: 443691 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.0839. Min Act: -0.0000

Data Index: 1077985 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 2.3306. Min Range: -2.3306

Max Act: 1.8604. Min Act: -0.0001

Data Index: 1053640 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.0907. Min Act: -0.0000

Data Index: 1269648 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.0650. Min Act: -0.0000

Data Index: 870651 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.0334. Min Act: -0.0000

Data Index: 594047 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 2.3306. Min Range: -2.3306

Max Act: 1.8369. Min Act: -0.0001

Data Index: 798959 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 2.3306. Min Range: -2.3306

Max Act: 1.8023. Min Act: -0.0000

Data Index: 704512 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 2.3306. Min Range: -2.3306

Max Act: 1.8719. Min Act: -0.0000

Data Index: 1303922 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 2.3306. Min Range: -2.3306

Max Act: 1.8702. Min Act: -0.0001

Data Index: 30529 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 2.3306. Min Range: -2.3306

Max Act: 1.8593. Min Act: -0.0000

Data Index: 1297373 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 2.3306. Min Range: -2.3306

Max Act: 1.9580. Min Act: -0.0000

Data Index: 448354 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 2.3306. Min Range: -2.3306

Max Act: 1.8074. Min Act: -0.0000

Data Index: 250115 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 2.3306. Min Range: -2.3306

Max Act: 1.7160. Min Act: -0.0000

Data Index: 725478 (C4 (Web Text))

Max Activating Token Index: 632