Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3541 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5382. Min Range: -1.5382

Max Act: 1.5382. Min Act: -0.0000

Data Index: 947113 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 1.5382. Min Range: -1.5382

Max Act: 1.2638. Min Act: -0.0000

Data Index: 546406 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 1.5382. Min Range: -1.5382

Max Act: 1.2155. Min Act: -0.0001

Data Index: 69611 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 1.5382. Min Range: -1.5382

Max Act: 1.2948. Min Act: -0.0001

Data Index: 454776 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 1.5382. Min Range: -1.5382

Max Act: 1.1150. Min Act: -0.0000

Data Index: 469632 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 1.5382. Min Range: -1.5382

Max Act: 1.1241. Min Act: -0.0000

Data Index: 612725 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 1.5382. Min Range: -1.5382

Max Act: 1.1099. Min Act: -0.0000

Data Index: 57049 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 1.5382. Min Range: -1.5382

Max Act: 1.1071. Min Act: -0.0001

Data Index: 931970 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 1.5382. Min Range: -1.5382

Max Act: 1.0675. Min Act: -0.0001

Data Index: 680460 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 1.5382. Min Range: -1.5382

Max Act: 1.0397. Min Act: -0.0001

Data Index: 1294120 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 1.5382. Min Range: -1.5382

Max Act: 1.0562. Min Act: -0.0000

Data Index: 428809 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 1.5382. Min Range: -1.5382

Max Act: 1.0830. Min Act: -0.0001

Data Index: 131930 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 1.5382. Min Range: -1.5382

Max Act: 1.0625. Min Act: -0.0000

Data Index: 1182647 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 1.5382. Min Range: -1.5382

Max Act: 1.0039. Min Act: -0.0000

Data Index: 249738 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 1.5382. Min Range: -1.5382

Max Act: 0.9681. Min Act: -0.0001

Data Index: 140746 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 1.5382. Min Range: -1.5382

Max Act: 1.0511. Min Act: -0.0000

Data Index: 1347855 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 1.5382. Min Range: -1.5382

Max Act: 1.0504. Min Act: -0.0000

Data Index: 769897 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 1.5382. Min Range: -1.5382

Max Act: 0.9567. Min Act: -0.0000

Data Index: 561094 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 1.5382. Min Range: -1.5382

Max Act: 0.9847. Min Act: -0.0001

Data Index: 80878 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 1.5382. Min Range: -1.5382

Max Act: 1.0163. Min Act: -0.0000

Data Index: 1036882 (C4 (Web Text))

Max Activating Token Index: 54