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

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

Neuron 3307 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.4451. Min Act: -0.0001

Data Index: 235732 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.4804. Min Act: -0.0001

Data Index: 166203 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.4127. Min Act: -0.0002

Data Index: 356848 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.4322. Min Act: -0.0002

Data Index: 478484 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.3409. Min Act: -0.0002

Data Index: 858421 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.3303. Min Act: -0.0001

Data Index: 501669 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.3716. Min Act: -0.0002

Data Index: 106927 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.3866. Min Act: -0.0002

Data Index: 1284901 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.3830. Min Act: -0.0002

Data Index: 616028 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.3270. Min Act: -0.0001

Data Index: 621412 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.2350. Min Act: -0.0001

Data Index: 1015950 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.3245. Min Act: -0.0002

Data Index: 272850 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.3247. Min Act: -0.0002

Data Index: 511202 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.1418. Min Act: -0.0001

Data Index: 875499 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.1847. Min Act: -0.0001

Data Index: 1031208 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.2309. Min Act: -0.0002

Data Index: 728420 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.1948. Min Act: -0.0001

Data Index: 251201 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.2197. Min Act: -0.0002

Data Index: 771010 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.1466. Min Act: -0.0001

Data Index: 321346 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 1.4804. Min Range: -1.4804

Max Act: 1.1395. Min Act: -0.0001

Data Index: 1011122 (C4 (Web Text))

Max Activating Token Index: 496