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

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

Neuron 4151 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0841. Min Range: -1.0841

Max Act: 1.0841. Min Act: -0.0000

Data Index: 775732 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 1.0841. Min Range: -1.0841

Max Act: 1.0377. Min Act: -0.0000

Data Index: 858243 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 1.0841. Min Range: -1.0841

Max Act: 1.0601. Min Act: 0.0000

Data Index: 194104 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 1.0841. Min Range: -1.0841

Max Act: 1.0010. Min Act: -0.0000

Data Index: 174311 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.9372. Min Act: -0.0000

Data Index: 957475 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.9661. Min Act: 0.0000

Data Index: 1062489 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.9834. Min Act: -0.0000

Data Index: 202387 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.9709. Min Act: -0.0000

Data Index: 1327191 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.9352. Min Act: -0.0000

Data Index: 512612 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.9446. Min Act: -0.0000

Data Index: 484889 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.9218. Min Act: -0.0000

Data Index: 846764 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.9156. Min Act: -0.0000

Data Index: 295547 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.9049. Min Act: -0.0000

Data Index: 834514 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.8690. Min Act: -0.0000

Data Index: 192483 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.8931. Min Act: -0.0000

Data Index: 474948 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.9125. Min Act: -0.0000

Data Index: 987949 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.8994. Min Act: -0.0000

Data Index: 808094 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.8680. Min Act: -0.0000

Data Index: 425572 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.9208. Min Act: -0.0000

Data Index: 313204 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.9094. Min Act: -0.0000

Data Index: 454459 (C4 (Web Text))

Max Activating Token Index: 248