Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1134 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4189. Min Range: -1.4189

Max Act: 1.3697. Min Act: -0.0000

Data Index: 1653045 (Python Code)

Max Activating Token Index: 756

Text #1

Max Range: 1.4189. Min Range: -1.4189

Max Act: 1.4189. Min Act: -0.0000

Data Index: 1394490 (Python Code)

Max Activating Token Index: 866

Text #2

Max Range: 1.4189. Min Range: -1.4189

Max Act: 1.1550. Min Act: -0.0000

Data Index: 95161 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 1.4189. Min Range: -1.4189

Max Act: 1.1514. Min Act: -0.0000

Data Index: 343164 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 1.4189. Min Range: -1.4189

Max Act: 1.2058. Min Act: -0.0000

Data Index: 1120262 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 1.4189. Min Range: -1.4189

Max Act: 1.1913. Min Act: -0.0000

Data Index: 1590314 (Python Code)

Max Activating Token Index: 205

Text #6

Max Range: 1.4189. Min Range: -1.4189

Max Act: 1.0862. Min Act: -0.0000

Data Index: 447063 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 1.4189. Min Range: -1.4189

Max Act: 1.0911. Min Act: -0.0000

Data Index: 658604 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 1.4189. Min Range: -1.4189

Max Act: 1.0675. Min Act: -0.0000

Data Index: 639138 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 1.4189. Min Range: -1.4189

Max Act: 1.0228. Min Act: -0.0000

Data Index: 338144 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 1.4189. Min Range: -1.4189

Max Act: 1.0567. Min Act: -0.0000

Data Index: 1302826 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 1.4189. Min Range: -1.4189

Max Act: 0.9760. Min Act: -0.0000

Data Index: 808206 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 1.4189. Min Range: -1.4189

Max Act: 0.9628. Min Act: -0.0000

Data Index: 161437 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 1.4189. Min Range: -1.4189

Max Act: 0.8901. Min Act: -0.0000

Data Index: 114024 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 1.4189. Min Range: -1.4189

Max Act: 0.9398. Min Act: -0.0000

Data Index: 46530 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 1.4189. Min Range: -1.4189

Max Act: 0.9623. Min Act: -0.0000

Data Index: 192265 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 1.4189. Min Range: -1.4189

Max Act: 0.8285. Min Act: -0.0000

Data Index: 687285 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 1.4189. Min Range: -1.4189

Max Act: 0.9150. Min Act: -0.0000

Data Index: 1145929 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 1.4189. Min Range: -1.4189

Max Act: 0.9141. Min Act: -0.0000

Data Index: 799064 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 1.4189. Min Range: -1.4189

Max Act: 0.8781. Min Act: -0.0000

Data Index: 1313223 (C4 (Web Text))

Max Activating Token Index: 728