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

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

Neuron 4975 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9118. Min Range: -2.9118

Max Act: 2.9118. Min Act: -0.0000

Data Index: 987123 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 2.9118. Min Range: -2.9118

Max Act: 2.7990. Min Act: -0.0000

Data Index: 442755 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 2.9118. Min Range: -2.9118

Max Act: 2.1719. Min Act: -0.0000

Data Index: 661985 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 2.9118. Min Range: -2.9118

Max Act: 2.0133. Min Act: -0.0000

Data Index: 1108361 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 2.9118. Min Range: -2.9118

Max Act: 2.0014. Min Act: -0.0000

Data Index: 45964 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 2.9118. Min Range: -2.9118

Max Act: 2.1180. Min Act: -0.0000

Data Index: 628909 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 2.9118. Min Range: -2.9118

Max Act: 1.8957. Min Act: -0.0000

Data Index: 9340 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 2.9118. Min Range: -2.9118

Max Act: 1.7320. Min Act: -0.0000

Data Index: 210586 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 2.9118. Min Range: -2.9118

Max Act: 1.7454. Min Act: -0.0000

Data Index: 105319 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 2.9118. Min Range: -2.9118

Max Act: 1.6637. Min Act: -0.0000

Data Index: 762532 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 2.9118. Min Range: -2.9118

Max Act: 1.6519. Min Act: -0.0000

Data Index: 97315 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 2.9118. Min Range: -2.9118

Max Act: 1.6587. Min Act: -0.0000

Data Index: 776397 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 2.9118. Min Range: -2.9118

Max Act: 1.5206. Min Act: -0.0000

Data Index: 1019904 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 2.9118. Min Range: -2.9118

Max Act: 1.6061. Min Act: -0.0000

Data Index: 362304 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 2.9118. Min Range: -2.9118

Max Act: 1.5878. Min Act: -0.0000

Data Index: 1024433 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 2.9118. Min Range: -2.9118

Max Act: 1.6729. Min Act: -0.0000

Data Index: 1350415 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 2.9118. Min Range: -2.9118

Max Act: 1.6632. Min Act: -0.0000

Data Index: 46158 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 2.9118. Min Range: -2.9118

Max Act: 1.6205. Min Act: -0.0000

Data Index: 743606 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 2.9118. Min Range: -2.9118

Max Act: 1.5253. Min Act: -0.0000

Data Index: 886388 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 2.9118. Min Range: -2.9118

Max Act: 1.5152. Min Act: -0.0000

Data Index: 1087334 (C4 (Web Text))

Max Activating Token Index: 464