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

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

Neuron 1831 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.5825. Min Act: -0.0000

Data Index: 1206556 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.3044. Min Act: -0.0000

Data Index: 787679 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.6907. Min Act: -0.0000

Data Index: 449650 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.2769. Min Act: -0.0000

Data Index: 1306908 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.2911. Min Act: -0.0000

Data Index: 829236 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.2107. Min Act: -0.0000

Data Index: 163659 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 3.6907. Min Range: -3.6907

Max Act: 2.8484. Min Act: -0.0000

Data Index: 11957 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 3.6907. Min Range: -3.6907

Max Act: 2.6849. Min Act: -0.0000

Data Index: 343022 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 3.6907. Min Range: -3.6907

Max Act: 2.8379. Min Act: -0.0000

Data Index: 245810 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 3.6907. Min Range: -3.6907

Max Act: 2.7675. Min Act: -0.0000

Data Index: 1242599 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 3.6907. Min Range: -3.6907

Max Act: 2.6369. Min Act: -0.0000

Data Index: 869822 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 3.6907. Min Range: -3.6907

Max Act: 2.7374. Min Act: -0.0000

Data Index: 567101 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 3.6907. Min Range: -3.6907

Max Act: 2.6057. Min Act: -0.0000

Data Index: 1314356 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 3.6907. Min Range: -3.6907

Max Act: 2.5179. Min Act: -0.0000

Data Index: 347428 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 3.6907. Min Range: -3.6907

Max Act: 2.3748. Min Act: -0.0000

Data Index: 981930 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 3.6907. Min Range: -3.6907

Max Act: 2.4807. Min Act: -0.0000

Data Index: 41894 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 3.6907. Min Range: -3.6907

Max Act: 2.3283. Min Act: -0.0000

Data Index: 329315 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 3.6907. Min Range: -3.6907

Max Act: 2.4212. Min Act: -0.0000

Data Index: 1005885 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 3.6907. Min Range: -3.6907

Max Act: 2.2328. Min Act: -0.0000

Data Index: 747341 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 3.6907. Min Range: -3.6907

Max Act: 2.3583. Min Act: -0.0000

Data Index: 124614 (C4 (Web Text))

Max Activating Token Index: 627