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

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

Neuron 1772 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: 0.1102. Min Range: -0.1102

Max Act: 0.1102. Min Act: -0.0003

Data Index: 443972 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.1017. Min Act: -0.0003

Data Index: 867040 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0937. Min Act: -0.0003

Data Index: 100189 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0973. Min Act: -0.0003

Data Index: 458882 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.1055. Min Act: -0.0003

Data Index: 854266 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0976. Min Act: -0.0003

Data Index: 1335464 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0993. Min Act: -0.0003

Data Index: 338909 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.1033. Min Act: -0.0003

Data Index: 732248 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0981. Min Act: -0.0003

Data Index: 1148125 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0948. Min Act: -0.0003

Data Index: 18255 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0942. Min Act: -0.0003

Data Index: 473453 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0977. Min Act: -0.0003

Data Index: 248634 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0937. Min Act: -0.0003

Data Index: 733349 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0931. Min Act: -0.0003

Data Index: 716636 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0948. Min Act: -0.0003

Data Index: 161423 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0916. Min Act: -0.0003

Data Index: 665198 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.1062. Min Act: -0.0003

Data Index: 735312 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0877. Min Act: -0.0003

Data Index: 1094249 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0895. Min Act: -0.0003

Data Index: 195132 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.1102. Min Range: -0.1102

Max Act: 0.0974. Min Act: -0.0003

Data Index: 119950 (C4 (Web Text))

Max Activating Token Index: 70