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

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

Neuron 2935 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5336. Min Range: -2.5336

Max Act: 2.5336. Min Act: -0.0000

Data Index: 713801 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 2.5336. Min Range: -2.5336

Max Act: 2.3972. Min Act: -0.0000

Data Index: 560158 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 2.5336. Min Range: -2.5336

Max Act: 2.2690. Min Act: -0.0000

Data Index: 835133 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 2.5336. Min Range: -2.5336

Max Act: 2.1987. Min Act: -0.0000

Data Index: 885993 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 2.5336. Min Range: -2.5336

Max Act: 2.2665. Min Act: -0.0000

Data Index: 761659 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 2.5336. Min Range: -2.5336

Max Act: 1.9689. Min Act: -0.0000

Data Index: 774030 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 2.5336. Min Range: -2.5336

Max Act: 1.8100. Min Act: -0.0000

Data Index: 985029 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 2.5336. Min Range: -2.5336

Max Act: 1.8252. Min Act: -0.0000

Data Index: 188468 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 2.5336. Min Range: -2.5336

Max Act: 1.7934. Min Act: -0.0000

Data Index: 353922 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 2.5336. Min Range: -2.5336

Max Act: 1.7211. Min Act: -0.0000

Data Index: 979008 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 2.5336. Min Range: -2.5336

Max Act: 1.7048. Min Act: -0.0000

Data Index: 128486 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 2.5336. Min Range: -2.5336

Max Act: 1.6246. Min Act: -0.0000

Data Index: 920830 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 2.5336. Min Range: -2.5336

Max Act: 1.5880. Min Act: -0.0000

Data Index: 1115929 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 2.5336. Min Range: -2.5336

Max Act: 1.4847. Min Act: -0.0000

Data Index: 813573 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 2.5336. Min Range: -2.5336

Max Act: 1.5420. Min Act: -0.0000

Data Index: 345255 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 2.5336. Min Range: -2.5336

Max Act: 1.5355. Min Act: -0.0000

Data Index: 232353 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 2.5336. Min Range: -2.5336

Max Act: 1.5308. Min Act: -0.0000

Data Index: 878790 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 2.5336. Min Range: -2.5336

Max Act: 1.5782. Min Act: -0.0000

Data Index: 12276 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 2.5336. Min Range: -2.5336

Max Act: 1.3668. Min Act: -0.0000

Data Index: 1184195 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 2.5336. Min Range: -2.5336

Max Act: 1.4501. Min Act: -0.0000

Data Index: 544001 (C4 (Web Text))

Max Activating Token Index: 891