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

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

Neuron 3116 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.9708. Min Act: -0.0001

Data Index: 232729 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.9398. Min Act: -0.0001

Data Index: 647370 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.6965. Min Act: -0.0001

Data Index: 1213712 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.4929. Min Act: -0.0001

Data Index: 664934 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.3598. Min Act: -0.0001

Data Index: 315553 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.3424. Min Act: -0.0001

Data Index: 109063 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.0404. Min Act: -0.0001

Data Index: 433880 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.1484. Min Act: -0.0001

Data Index: 1303863 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.2761. Min Act: -0.0001

Data Index: 788972 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.0140. Min Act: -0.0001

Data Index: 906439 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 3.9708. Min Range: -3.9708

Max Act: 2.9786. Min Act: -0.0001

Data Index: 604316 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.2649. Min Act: -0.0001

Data Index: 670784 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.1218. Min Act: -0.0001

Data Index: 464376 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.0518. Min Act: -0.0001

Data Index: 1047818 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.3723. Min Act: -0.0001

Data Index: 148522 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.3405. Min Act: -0.0001

Data Index: 930166 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.0565. Min Act: -0.0001

Data Index: 713210 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.0566. Min Act: -0.0001

Data Index: 1133493 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.0487. Min Act: -0.0001

Data Index: 418679 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.1849. Min Act: -0.0001

Data Index: 41262 (C4 (Web Text))

Max Activating Token Index: 40