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

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

Neuron 1837 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0012. Min Range: -3.0012

Max Act: 3.0012. Min Act: -0.0000

Data Index: 826855 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.6865. Min Act: -0.0000

Data Index: 218425 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.7906. Min Act: -0.0000

Data Index: 1357795 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.6277. Min Act: -0.0000

Data Index: 268695 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.6848. Min Act: -0.0000

Data Index: 273959 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.3357. Min Act: -0.0000

Data Index: 205982 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.5487. Min Act: -0.0000

Data Index: 370636 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.5250. Min Act: -0.0000

Data Index: 1209201 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.3743. Min Act: -0.0000

Data Index: 643424 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.5046. Min Act: -0.0000

Data Index: 1286497 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.4047. Min Act: -0.0000

Data Index: 98827 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.3733. Min Act: -0.0000

Data Index: 805589 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.3464. Min Act: -0.0000

Data Index: 557848 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.4322. Min Act: -0.0000

Data Index: 292437 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.3256. Min Act: -0.0000

Data Index: 1004359 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.3181. Min Act: -0.0000

Data Index: 288900 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.2923. Min Act: -0.0000

Data Index: 751007 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.1612. Min Act: -0.0000

Data Index: 1117846 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.1410. Min Act: -0.0000

Data Index: 25504 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.2647. Min Act: -0.0000

Data Index: 994175 (C4 (Web Text))

Max Activating Token Index: 261