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

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

Neuron 1826 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1059. Min Range: -5.1059

Max Act: 5.1059. Min Act: -0.0000

Data Index: 421116 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 5.1059. Min Range: -5.1059

Max Act: 4.7487. Min Act: -0.0000

Data Index: 773172 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 5.1059. Min Range: -5.1059

Max Act: 4.4352. Min Act: -0.0000

Data Index: 356154 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 5.1059. Min Range: -5.1059

Max Act: 4.0841. Min Act: -0.0000

Data Index: 439995 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 5.1059. Min Range: -5.1059

Max Act: 4.2116. Min Act: -0.0000

Data Index: 781643 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 5.1059. Min Range: -5.1059

Max Act: 4.3332. Min Act: -0.0000

Data Index: 372803 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 5.1059. Min Range: -5.1059

Max Act: 4.1540. Min Act: -0.0000

Data Index: 240785 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 5.1059. Min Range: -5.1059

Max Act: 4.2156. Min Act: -0.0000

Data Index: 667447 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 5.1059. Min Range: -5.1059

Max Act: 4.0227. Min Act: -0.0000

Data Index: 98682 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 5.1059. Min Range: -5.1059

Max Act: 3.9135. Min Act: -0.0000

Data Index: 1211410 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 5.1059. Min Range: -5.1059

Max Act: 4.1059. Min Act: -0.0000

Data Index: 1092201 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 5.1059. Min Range: -5.1059

Max Act: 3.9349. Min Act: -0.0000

Data Index: 1191157 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 5.1059. Min Range: -5.1059

Max Act: 3.7336. Min Act: -0.0000

Data Index: 165660 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 5.1059. Min Range: -5.1059

Max Act: 3.8724. Min Act: -0.0000

Data Index: 502269 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 5.1059. Min Range: -5.1059

Max Act: 3.8528. Min Act: -0.0000

Data Index: 1126241 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 5.1059. Min Range: -5.1059

Max Act: 3.9247. Min Act: -0.0000

Data Index: 231211 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 5.1059. Min Range: -5.1059

Max Act: 3.6094. Min Act: -0.0000

Data Index: 1354001 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 5.1059. Min Range: -5.1059

Max Act: 3.5187. Min Act: -0.0000

Data Index: 658036 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 5.1059. Min Range: -5.1059

Max Act: 3.6593. Min Act: -0.0000

Data Index: 790194 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 5.1059. Min Range: -5.1059

Max Act: 3.6386. Min Act: -0.0000

Data Index: 687837 (C4 (Web Text))

Max Activating Token Index: 134