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

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

Neuron 42 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: 6.0127. Min Range: -6.0127

Max Act: 6.0127. Min Act: -0.0000

Data Index: 586182 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 6.0127. Min Range: -6.0127

Max Act: 5.5675. Min Act: -0.0000

Data Index: 603386 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 6.0127. Min Range: -6.0127

Max Act: 4.5205. Min Act: -0.0000

Data Index: 1171479 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 6.0127. Min Range: -6.0127

Max Act: 4.2520. Min Act: -0.0000

Data Index: 1070860 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 6.0127. Min Range: -6.0127

Max Act: 4.5975. Min Act: -0.0000

Data Index: 161821 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 6.0127. Min Range: -6.0127

Max Act: 3.9261. Min Act: -0.0000

Data Index: 776227 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 6.0127. Min Range: -6.0127

Max Act: 4.4504. Min Act: -0.0000

Data Index: 756406 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 6.0127. Min Range: -6.0127

Max Act: 3.9426. Min Act: -0.0000

Data Index: 755460 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 6.0127. Min Range: -6.0127

Max Act: 4.3027. Min Act: -0.0000

Data Index: 132935 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 6.0127. Min Range: -6.0127

Max Act: 3.7515. Min Act: -0.0000

Data Index: 1123305 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 6.0127. Min Range: -6.0127

Max Act: 4.4218. Min Act: -0.0000

Data Index: 63297 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 6.0127. Min Range: -6.0127

Max Act: 3.7404. Min Act: -0.0000

Data Index: 670515 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 6.0127. Min Range: -6.0127

Max Act: 4.0147. Min Act: -0.0000

Data Index: 1188464 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 6.0127. Min Range: -6.0127

Max Act: 3.8458. Min Act: -0.0000

Data Index: 838875 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 6.0127. Min Range: -6.0127

Max Act: 4.0977. Min Act: -0.0000

Data Index: 476303 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 6.0127. Min Range: -6.0127

Max Act: 3.9042. Min Act: -0.0000

Data Index: 188378 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 6.0127. Min Range: -6.0127

Max Act: 4.0364. Min Act: -0.0000

Data Index: 297548 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 6.0127. Min Range: -6.0127

Max Act: 3.3580. Min Act: -0.0000

Data Index: 437203 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 6.0127. Min Range: -6.0127

Max Act: 3.6263. Min Act: -0.0000

Data Index: 700405 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 6.0127. Min Range: -6.0127

Max Act: 3.7655. Min Act: -0.0000

Data Index: 380973 (C4 (Web Text))

Max Activating Token Index: 320