Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3983 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0742. Min Act: -0.0001

Data Index: 830563 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0563. Min Act: -0.0001

Data Index: 880134 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0634. Min Act: -0.0001

Data Index: 734132 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0508. Min Act: -0.0001

Data Index: 939326 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0481. Min Act: -0.0001

Data Index: 1338965 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0414. Min Act: -0.0001

Data Index: 875796 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0440. Min Act: -0.0001

Data Index: 575712 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0417. Min Act: -0.0001

Data Index: 456534 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0429. Min Act: -0.0001

Data Index: 482581 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0444. Min Act: -0.0001

Data Index: 489521 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0409. Min Act: -0.0001

Data Index: 566272 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0449. Min Act: -0.0001

Data Index: 1200783 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0385. Min Act: -0.0001

Data Index: 188855 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0426. Min Act: -0.0001

Data Index: 52349 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0378. Min Act: -0.0001

Data Index: 1012688 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0413. Min Act: -0.0001

Data Index: 756380 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0413. Min Act: -0.0001

Data Index: 6561 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0412. Min Act: -0.0001

Data Index: 503741 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0409. Min Act: -0.0001

Data Index: 66021 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0406. Min Act: -0.0001

Data Index: 576422 (C4 (Web Text))

Max Activating Token Index: 676