Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4612 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1178. Min Range: -1.1178

Max Act: 1.1178. Min Act: -0.0001

Data Index: 1047005 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 1.1178. Min Range: -1.1178

Max Act: 0.9683. Min Act: -0.0001

Data Index: 278309 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 1.1178. Min Range: -1.1178

Max Act: 0.9005. Min Act: -0.0001

Data Index: 424556 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 1.1178. Min Range: -1.1178

Max Act: 0.8439. Min Act: -0.0001

Data Index: 715708 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 1.1178. Min Range: -1.1178

Max Act: 0.9065. Min Act: -0.0001

Data Index: 39037 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 1.1178. Min Range: -1.1178

Max Act: 0.8512. Min Act: -0.0001

Data Index: 1322079 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 1.1178. Min Range: -1.1178

Max Act: 0.7895. Min Act: -0.0001

Data Index: 880667 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 1.1178. Min Range: -1.1178

Max Act: 0.8312. Min Act: -0.0001

Data Index: 1196951 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 1.1178. Min Range: -1.1178

Max Act: 0.8376. Min Act: -0.0001

Data Index: 357619 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 1.1178. Min Range: -1.1178

Max Act: 0.8070. Min Act: -0.0001

Data Index: 592954 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 1.1178. Min Range: -1.1178

Max Act: 0.7669. Min Act: -0.0001

Data Index: 77071 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 1.1178. Min Range: -1.1178

Max Act: 0.8026. Min Act: -0.0001

Data Index: 1027104 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 1.1178. Min Range: -1.1178

Max Act: 0.7949. Min Act: -0.0001

Data Index: 492646 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 1.1178. Min Range: -1.1178

Max Act: 0.7601. Min Act: -0.0001

Data Index: 106232 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 1.1178. Min Range: -1.1178

Max Act: 0.6808. Min Act: -0.0001

Data Index: 708761 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 1.1178. Min Range: -1.1178

Max Act: 0.7465. Min Act: -0.0001

Data Index: 1207633 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 1.1178. Min Range: -1.1178

Max Act: 0.6797. Min Act: -0.0001

Data Index: 1082730 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 1.1178. Min Range: -1.1178

Max Act: 0.7500. Min Act: -0.0001

Data Index: 90403 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 1.1178. Min Range: -1.1178

Max Act: 0.7274. Min Act: -0.0001

Data Index: 90940 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 1.1178. Min Range: -1.1178

Max Act: 0.7108. Min Act: -0.0001

Data Index: 322309 (C4 (Web Text))

Max Activating Token Index: 44