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

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

Neuron 2790 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: 2.7128. Min Range: -2.7128

Max Act: 2.7034. Min Act: -0.0000

Data Index: 287691 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 2.7128. Min Range: -2.7128

Max Act: 2.7128. Min Act: -0.0000

Data Index: 1421773 (Python Code)

Max Activating Token Index: 999

Text #2

Max Range: 2.7128. Min Range: -2.7128

Max Act: 2.5704. Min Act: -0.0000

Data Index: 1136325 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 2.7128. Min Range: -2.7128

Max Act: 2.5295. Min Act: -0.0000

Data Index: 605102 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 2.7128. Min Range: -2.7128

Max Act: 2.4616. Min Act: -0.0000

Data Index: 933748 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 2.7128. Min Range: -2.7128

Max Act: 2.4332. Min Act: -0.0000

Data Index: 199093 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 2.7128. Min Range: -2.7128

Max Act: 2.4331. Min Act: -0.0000

Data Index: 178046 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 2.7128. Min Range: -2.7128

Max Act: 2.2933. Min Act: -0.0000

Data Index: 286546 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 2.7128. Min Range: -2.7128

Max Act: 2.3992. Min Act: -0.0000

Data Index: 957540 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 2.7128. Min Range: -2.7128

Max Act: 2.3874. Min Act: -0.0000

Data Index: 960952 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 2.7128. Min Range: -2.7128

Max Act: 2.3968. Min Act: -0.0000

Data Index: 1138515 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 2.7128. Min Range: -2.7128

Max Act: 2.3187. Min Act: -0.0000

Data Index: 288161 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 2.7128. Min Range: -2.7128

Max Act: 2.1316. Min Act: -0.0000

Data Index: 709908 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 2.7128. Min Range: -2.7128

Max Act: 2.2453. Min Act: -0.0000

Data Index: 298099 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 2.7128. Min Range: -2.7128

Max Act: 2.1278. Min Act: -0.0000

Data Index: 24549 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 2.7128. Min Range: -2.7128

Max Act: 2.1095. Min Act: -0.0000

Data Index: 1403269 (Python Code)

Max Activating Token Index: 812

Text #16

Max Range: 2.7128. Min Range: -2.7128

Max Act: 2.1047. Min Act: -0.0000

Data Index: 550453 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 2.7128. Min Range: -2.7128

Max Act: 2.1060. Min Act: -0.0000

Data Index: 1326247 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 2.7128. Min Range: -2.7128

Max Act: 2.1650. Min Act: -0.0000

Data Index: 241643 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 2.7128. Min Range: -2.7128

Max Act: 2.1680. Min Act: -0.0000

Data Index: 965526 (C4 (Web Text))

Max Activating Token Index: 880