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

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

Neuron 4199 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: 2.5281. Min Range: -2.5281

Max Act: 2.5281. Min Act: -0.0000

Data Index: 981713 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.1598. Min Act: -0.0000

Data Index: 1357773 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.1269. Min Act: -0.0000

Data Index: 1537288 (Python Code)

Max Activating Token Index: 171

Text #3

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.2393. Min Act: -0.0000

Data Index: 299669 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 2.5281. Min Range: -2.5281

Max Act: 1.9458. Min Act: -0.0000

Data Index: 236744 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.0353. Min Act: -0.0000

Data Index: 903877 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 2.5281. Min Range: -2.5281

Max Act: 1.9232. Min Act: -0.0000

Data Index: 649826 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.0223. Min Act: -0.0000

Data Index: 1118268 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 2.5281. Min Range: -2.5281

Max Act: 1.9194. Min Act: -0.0000

Data Index: 299078 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.0236. Min Act: -0.0000

Data Index: 250229 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.0062. Min Act: -0.0000

Data Index: 37668 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 2.5281. Min Range: -2.5281

Max Act: 1.9935. Min Act: -0.0000

Data Index: 1490512 (Python Code)

Max Activating Token Index: 896

Text #12

Max Range: 2.5281. Min Range: -2.5281

Max Act: 1.8714. Min Act: -0.0000

Data Index: 262459 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 2.5281. Min Range: -2.5281

Max Act: 1.9575. Min Act: -0.0000

Data Index: 93150 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 2.5281. Min Range: -2.5281

Max Act: 1.8499. Min Act: -0.0000

Data Index: 195737 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 2.5281. Min Range: -2.5281

Max Act: 1.9422. Min Act: -0.0000

Data Index: 32507 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 2.5281. Min Range: -2.5281

Max Act: 1.9336. Min Act: -0.0000

Data Index: 297648 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 2.5281. Min Range: -2.5281

Max Act: 1.8070. Min Act: -0.0000

Data Index: 1231480 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 2.5281. Min Range: -2.5281

Max Act: 1.9317. Min Act: -0.0000

Data Index: 284166 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 2.5281. Min Range: -2.5281

Max Act: 2.0182. Min Act: -0.0000

Data Index: 666217 (C4 (Web Text))

Max Activating Token Index: 880