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

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

Neuron 3693 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1637. Min Range: -4.1637

Max Act: 4.1144. Min Act: -0.0000

Data Index: 115751 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.7083. Min Act: -0.0000

Data Index: 1684 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 4.1637. Min Range: -4.1637

Max Act: 4.1637. Min Act: -0.0000

Data Index: 1019488 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 4.1637. Min Range: -4.1637

Max Act: 4.0967. Min Act: -0.0001

Data Index: 1287711 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.9315. Min Act: -0.0001

Data Index: 340179 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.5781. Min Act: -0.0001

Data Index: 525178 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.9222. Min Act: -0.0000

Data Index: 1219711 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.5772. Min Act: -0.0000

Data Index: 957617 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.5636. Min Act: -0.0000

Data Index: 368438 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.6854. Min Act: -0.0000

Data Index: 561969 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.4955. Min Act: -0.0000

Data Index: 90376 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.7828. Min Act: -0.0000

Data Index: 1049597 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.3607. Min Act: -0.0000

Data Index: 576621 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.3497. Min Act: -0.0000

Data Index: 629228 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.3171. Min Act: -0.0000

Data Index: 130440 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.2302. Min Act: -0.0000

Data Index: 588635 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.0196. Min Act: -0.0001

Data Index: 1101311 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.1167. Min Act: -0.0001

Data Index: 245147 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.0888. Min Act: -0.0001

Data Index: 787712 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 4.1637. Min Range: -4.1637

Max Act: 2.9343. Min Act: -0.0000

Data Index: 1019487 (C4 (Web Text))

Max Activating Token Index: 501