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

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

Neuron 4554 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: 3.0470. Min Range: -3.0470

Max Act: 3.0470. Min Act: -0.0001

Data Index: 122532 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 3.0470. Min Range: -3.0470

Max Act: 3.0341. Min Act: -0.0000

Data Index: 138576 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 3.0470. Min Range: -3.0470

Max Act: 2.6610. Min Act: -0.0000

Data Index: 88547 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 3.0470. Min Range: -3.0470

Max Act: 2.7109. Min Act: -0.0000

Data Index: 937601 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 3.0470. Min Range: -3.0470

Max Act: 2.6059. Min Act: -0.0000

Data Index: 256837 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 3.0470. Min Range: -3.0470

Max Act: 2.5752. Min Act: -0.0000

Data Index: 723063 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 3.0470. Min Range: -3.0470

Max Act: 2.6334. Min Act: -0.0000

Data Index: 886339 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 3.0470. Min Range: -3.0470

Max Act: 2.7639. Min Act: -0.0001

Data Index: 195673 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 3.0470. Min Range: -3.0470

Max Act: 2.5347. Min Act: -0.0000

Data Index: 1219997 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 3.0470. Min Range: -3.0470

Max Act: 2.3820. Min Act: -0.0000

Data Index: 985381 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 3.0470. Min Range: -3.0470

Max Act: 2.2360. Min Act: -0.0000

Data Index: 535157 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 3.0470. Min Range: -3.0470

Max Act: 2.2248. Min Act: -0.0000

Data Index: 904175 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 3.0470. Min Range: -3.0470

Max Act: 2.4490. Min Act: -0.0000

Data Index: 201189 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 3.0470. Min Range: -3.0470

Max Act: 2.4504. Min Act: -0.0000

Data Index: 909326 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 3.0470. Min Range: -3.0470

Max Act: 2.3828. Min Act: -0.0001

Data Index: 658864 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 3.0470. Min Range: -3.0470

Max Act: 2.3736. Min Act: -0.0000

Data Index: 938555 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 3.0470. Min Range: -3.0470

Max Act: 2.2576. Min Act: -0.0000

Data Index: 1030539 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 3.0470. Min Range: -3.0470

Max Act: 2.2321. Min Act: -0.0001

Data Index: 1044017 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 3.0470. Min Range: -3.0470

Max Act: 2.3165. Min Act: -0.0000

Data Index: 1000979 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 3.0470. Min Range: -3.0470

Max Act: 2.6543. Min Act: -0.0000

Data Index: 543990 (C4 (Web Text))

Max Activating Token Index: 312