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

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

Neuron 2048 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: 0.4688. Min Range: -0.4688

Max Act: 0.4679. Min Act: -0.0000

Data Index: 866398 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1303880 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.4644. Min Act: -0.0000

Data Index: 263840 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.4688. Min Act: -0.0000

Data Index: 743415 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.4302. Min Act: -0.0000

Data Index: 232837 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.4139. Min Act: -0.0000

Data Index: 96340 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.4407. Min Act: -0.0000

Data Index: 979790 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1357716 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1359416 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3955. Min Act: -0.0000

Data Index: 36586 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3934. Min Act: -0.0000

Data Index: 512071 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3812. Min Act: -0.0000

Data Index: 648420 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1073988 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3762. Min Act: -0.0000

Data Index: 570126 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3566. Min Act: -0.0000

Data Index: 222612 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3444. Min Act: -0.0000

Data Index: 126658 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3490. Min Act: -0.0000

Data Index: 340897 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3418. Min Act: -0.0000

Data Index: 1340103 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3867. Min Act: -0.0000

Data Index: 1092061 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1002376 (C4 (Web Text))

Max Activating Token Index: 385