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

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

Neuron 3452 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.3426. Min Act: -0.0001

Data Index: 130640 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.3269. Min Act: -0.0001

Data Index: 900314 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2920. Min Act: -0.0001

Data Index: 526207 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2832. Min Act: -0.0000

Data Index: 1201479 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2804. Min Act: -0.0000

Data Index: 91170 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2656. Min Act: -0.0000

Data Index: 548080 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2769. Min Act: -0.0001

Data Index: 943764 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2873. Min Act: -0.0000

Data Index: 889200 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2516. Min Act: -0.0000

Data Index: 107616 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2831. Min Act: -0.0001

Data Index: 961658 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2539. Min Act: -0.0000

Data Index: 1292826 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2532. Min Act: -0.0001

Data Index: 1632784 (Python Code)

Max Activating Token Index: 907

Text #12

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2411. Min Act: -0.0000

Data Index: 1087244 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2661. Min Act: -0.0001

Data Index: 858610 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2340. Min Act: -0.0001

Data Index: 357709 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2385. Min Act: -0.0001

Data Index: 331606 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2396. Min Act: -0.0000

Data Index: 620992 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2472. Min Act: -0.0000

Data Index: 255034 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.1987. Min Act: -0.0001

Data Index: 292459 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.3426. Min Range: -0.3426

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1228027 (C4 (Web Text))

Max Activating Token Index: 20