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

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

Neuron 3507 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.4975. Min Act: -0.0001

Data Index: 939769 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.4322. Min Act: -0.0001

Data Index: 1118632 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.1605. Min Act: -0.0001

Data Index: 481960 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.1556. Min Act: -0.0001

Data Index: 826384 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.0794. Min Act: -0.0001

Data Index: 1244994 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.1009. Min Act: -0.0001

Data Index: 118113 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.0616. Min Act: -0.0001

Data Index: 154750 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9533. Min Act: -0.0001

Data Index: 617807 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.0676. Min Act: -0.0001

Data Index: 63119 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.0606. Min Act: -0.0001

Data Index: 700018 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9924. Min Act: -0.0001

Data Index: 901362 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9564. Min Act: -0.0001

Data Index: 374 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.0374. Min Act: -0.0001

Data Index: 355469 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.0036. Min Act: -0.0001

Data Index: 425859 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.0041. Min Act: -0.0001

Data Index: 570152 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9746. Min Act: -0.0001

Data Index: 1077532 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.0225. Min Act: -0.0001

Data Index: 331024 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9843. Min Act: -0.0001

Data Index: 1341599 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.8606. Min Act: -0.0001

Data Index: 370062 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9566. Min Act: -0.0001

Data Index: 454986 (C4 (Web Text))

Max Activating Token Index: 907