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

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

Neuron 4660 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1347985 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0520. Min Act: -0.0002

Data Index: 732133 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0467. Min Act: -0.0002

Data Index: 148942 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0397. Min Act: -0.0002

Data Index: 758665 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0390. Min Act: -0.0002

Data Index: 757903 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0396. Min Act: -0.0002

Data Index: 176022 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0380. Min Act: -0.0002

Data Index: 162047 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1160823 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0354. Min Act: -0.0002

Data Index: 964684 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0362. Min Act: -0.0002

Data Index: 183388 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1184672 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0335. Min Act: -0.0002

Data Index: 106188 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0349. Min Act: -0.0002

Data Index: 494621 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0342. Min Act: -0.0002

Data Index: 583916 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0333. Min Act: -0.0002

Data Index: 988565 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0340. Min Act: -0.0002

Data Index: 488935 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0332. Min Act: -0.0002

Data Index: 489921 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0336. Min Act: -0.0002

Data Index: 701035 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0341. Min Act: -0.0002

Data Index: 695333 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1316806 (C4 (Web Text))

Max Activating Token Index: 251