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

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

Neuron 2233 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: 8.9471. Min Range: -8.9471

Max Act: 8.9471. Min Act: -0.0000

Data Index: 1027435 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 8.9471. Min Range: -8.9471

Max Act: 7.1775. Min Act: 0.0000

Data Index: 729721 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 8.9471. Min Range: -8.9471

Max Act: 6.1500. Min Act: -0.0000

Data Index: 1231535 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 8.9471. Min Range: -8.9471

Max Act: 6.5998. Min Act: -0.0000

Data Index: 21885 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 8.9471. Min Range: -8.9471

Max Act: 6.7642. Min Act: 0.0000

Data Index: 535983 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 8.9471. Min Range: -8.9471

Max Act: 6.7054. Min Act: 0.0000

Data Index: 880942 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 8.9471. Min Range: -8.9471

Max Act: 4.6580. Min Act: 0.0000

Data Index: 861206 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 8.9471. Min Range: -8.9471

Max Act: 5.5081. Min Act: -0.0000

Data Index: 651504 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 8.9471. Min Range: -8.9471

Max Act: 5.7115. Min Act: -0.0000

Data Index: 247564 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 8.9471. Min Range: -8.9471

Max Act: 5.0483. Min Act: 0.0000

Data Index: 439195 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 8.9471. Min Range: -8.9471

Max Act: 4.8311. Min Act: -0.0000

Data Index: 138176 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 8.9471. Min Range: -8.9471

Max Act: 4.9563. Min Act: 0.0000

Data Index: 147667 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 8.9471. Min Range: -8.9471

Max Act: 5.4918. Min Act: 0.0000

Data Index: 991489 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 8.9471. Min Range: -8.9471

Max Act: 5.0508. Min Act: -0.0000

Data Index: 341387 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 8.9471. Min Range: -8.9471

Max Act: 5.8078. Min Act: -0.0000

Data Index: 437626 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 8.9471. Min Range: -8.9471

Max Act: 4.8186. Min Act: 0.0000

Data Index: 246239 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 8.9471. Min Range: -8.9471

Max Act: 5.1238. Min Act: -0.0000

Data Index: 355555 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 8.9471. Min Range: -8.9471

Max Act: 5.2035. Min Act: 0.0000

Data Index: 1238741 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 8.9471. Min Range: -8.9471

Max Act: 4.4250. Min Act: -0.0000

Data Index: 56282 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 8.9471. Min Range: -8.9471

Max Act: 4.5997. Min Act: -0.0000

Data Index: 750741 (C4 (Web Text))

Max Activating Token Index: 64