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

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

Neuron 803 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.6209. Min Act: -0.0001

Data Index: 74218 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.4566. Min Act: -0.0000

Data Index: 590234 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.3231. Min Act: -0.0000

Data Index: 926660 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.1465. Min Act: -0.0001

Data Index: 396506 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.1015. Min Act: -0.0001

Data Index: 163968 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 5.6209. Min Range: -5.6209

Max Act: 3.8857. Min Act: -0.0001

Data Index: 343144 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.0463. Min Act: -0.0000

Data Index: 574955 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.0345. Min Act: -0.0000

Data Index: 60989 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 5.6209. Min Range: -5.6209

Max Act: 3.7740. Min Act: -0.0000

Data Index: 34960 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.0894. Min Act: -0.0000

Data Index: 45840 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 5.6209. Min Range: -5.6209

Max Act: 3.7364. Min Act: -0.0000

Data Index: 10201 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.0482. Min Act: -0.0001

Data Index: 1178763 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 5.6209. Min Range: -5.6209

Max Act: 3.7174. Min Act: -0.0001

Data Index: 754483 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 5.6209. Min Range: -5.6209

Max Act: 3.9889. Min Act: -0.0000

Data Index: 702646 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 5.6209. Min Range: -5.6209

Max Act: 3.5620. Min Act: -0.0001

Data Index: 775079 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 5.6209. Min Range: -5.6209

Max Act: 3.7027. Min Act: -0.0000

Data Index: 758918 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 5.6209. Min Range: -5.6209

Max Act: 3.7002. Min Act: -0.0000

Data Index: 1257714 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 5.6209. Min Range: -5.6209

Max Act: 3.7029. Min Act: -0.0000

Data Index: 1202995 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 5.6209. Min Range: -5.6209

Max Act: 3.2007. Min Act: -0.0000

Data Index: 133380 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 5.6209. Min Range: -5.6209

Max Act: 3.6531. Min Act: -0.0000

Data Index: 377640 (C4 (Web Text))

Max Activating Token Index: 99