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

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

Neuron 3974 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.3555. Min Act: -0.0000

Data Index: 134387 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2866. Min Act: -0.0000

Data Index: 160912 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2771. Min Act: -0.0000

Data Index: 554012 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2748. Min Act: -0.0000

Data Index: 174093 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2725. Min Act: -0.0000

Data Index: 670531 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2737. Min Act: -0.0000

Data Index: 104812 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2609. Min Act: -0.0000

Data Index: 1245981 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2598. Min Act: 0.0000

Data Index: 879061 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2569. Min Act: -0.0000

Data Index: 1066384 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2465. Min Act: -0.0000

Data Index: 610789 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2599. Min Act: -0.0000

Data Index: 363057 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2268. Min Act: -0.0000

Data Index: 166613 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2492. Min Act: -0.0000

Data Index: 510103 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2415. Min Act: -0.0000

Data Index: 561242 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2333. Min Act: -0.0000

Data Index: 267433 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2291. Min Act: -0.0000

Data Index: 1096935 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2322. Min Act: -0.0000

Data Index: 1029118 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1036450 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2242. Min Act: -0.0000

Data Index: 396821 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 0.3555. Min Range: -0.3555

Max Act: 0.2384. Min Act: -0.0000

Data Index: 997282 (C4 (Web Text))

Max Activating Token Index: 267