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

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

Neuron 5987 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: 0.5533. Min Range: -0.5533

Max Act: 0.5332. Min Act: -0.0000

Data Index: 451706 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.5414. Min Act: -0.0000

Data Index: 749047 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.5057. Min Act: -0.0000

Data Index: 311490 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.5533. Min Act: -0.0000

Data Index: 782524 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.5191. Min Act: -0.0000

Data Index: 528819 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.5155. Min Act: -0.0000

Data Index: 177422 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4798. Min Act: -0.0000

Data Index: 232833 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4771. Min Act: -0.0000

Data Index: 32879 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.5217. Min Act: -0.0000

Data Index: 298799 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4915. Min Act: -0.0000

Data Index: 884933 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4740. Min Act: -0.0000

Data Index: 1197370 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1227365 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1052001 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1293121 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.5199. Min Act: -0.0000

Data Index: 696843 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.5047. Min Act: -0.0000

Data Index: 628676 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4711. Min Act: -0.0000

Data Index: 188782 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4806. Min Act: -0.0000

Data Index: 1073765 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.5081. Min Act: -0.0000

Data Index: 12103 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4888. Min Act: -0.0000

Data Index: 1078358 (C4 (Web Text))

Max Activating Token Index: 111