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

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

Neuron 508 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: 1.4164. Min Range: -1.4164

Max Act: 1.4164. Min Act: -0.0001

Data Index: 793241 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.3352. Min Act: -0.0001

Data Index: 568483 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.2711. Min Act: -0.0001

Data Index: 874487 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.3346. Min Act: -0.0001

Data Index: 160964 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.2571. Min Act: -0.0001

Data Index: 1055287 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.2465. Min Act: -0.0001

Data Index: 637234 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.1923. Min Act: -0.0001

Data Index: 28723 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.1589. Min Act: -0.0001

Data Index: 525290 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.1274. Min Act: -0.0001

Data Index: 730683 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.1502. Min Act: -0.0001

Data Index: 922079 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.1127. Min Act: -0.0001

Data Index: 154701 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.1086. Min Act: -0.0001

Data Index: 654608 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.1461. Min Act: -0.0001

Data Index: 9204 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.1427. Min Act: -0.0001

Data Index: 1060577 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.0309. Min Act: -0.0001

Data Index: 1275868 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.0903. Min Act: -0.0001

Data Index: 530648 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.0827. Min Act: -0.0001

Data Index: 1000310 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.0646. Min Act: -0.0001

Data Index: 478688 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.0598. Min Act: -0.0001

Data Index: 353733 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.0832. Min Act: -0.0001

Data Index: 159833 (C4 (Web Text))

Max Activating Token Index: 26