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

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

Neuron 3095 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1216. Min Act: -0.0003

Data Index: 57483 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1134. Min Act: -0.0003

Data Index: 275197 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1025. Min Act: -0.0003

Data Index: 530475 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0970. Min Act: -0.0002

Data Index: 697752 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0965. Min Act: -0.0003

Data Index: 615384 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0994. Min Act: -0.0003

Data Index: 1322772 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0993. Min Act: -0.0002

Data Index: 66064 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0995. Min Act: -0.0002

Data Index: 1359480 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0993. Min Act: -0.0003

Data Index: 395016 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0974. Min Act: -0.0002

Data Index: 108840 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0938. Min Act: -0.0002

Data Index: 1309045 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0937. Min Act: -0.0002

Data Index: 288099 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0967. Min Act: -0.0002

Data Index: 76979 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0930. Min Act: -0.0002

Data Index: 746326 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0931. Min Act: -0.0003

Data Index: 929345 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1127268 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0900. Min Act: -0.0002

Data Index: 622107 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0969. Min Act: -0.0002

Data Index: 907705 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1189974 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0897. Min Act: -0.0002

Data Index: 548641 (C4 (Web Text))

Max Activating Token Index: 15