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

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

Neuron 3006 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: 1.0166. Min Range: -1.0166

Max Act: 0.9969. Min Act: -0.0000

Data Index: 994805 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 1.0166. Min Range: -1.0166

Max Act: 1.0166. Min Act: -0.0000

Data Index: 949401 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.9454. Min Act: -0.0000

Data Index: 549870 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1199644 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.9218. Min Act: -0.0000

Data Index: 282344 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8277. Min Act: -0.0000

Data Index: 1168144 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.7997. Min Act: -0.0000

Data Index: 844829 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8183. Min Act: -0.0000

Data Index: 300901 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.7176. Min Act: -0.0000

Data Index: 192516 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.7179. Min Act: -0.0000

Data Index: 2413 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.6925. Min Act: -0.0000

Data Index: 245952 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.7166. Min Act: -0.0000

Data Index: 1179657 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.7219. Min Act: -0.0000

Data Index: 372346 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.6995. Min Act: -0.0000

Data Index: 425015 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.6565. Min Act: -0.0000

Data Index: 1067068 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.6454. Min Act: -0.0000

Data Index: 86786 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.6381. Min Act: -0.0000

Data Index: 323214 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.6796. Min Act: -0.0000

Data Index: 876901 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.6780. Min Act: -0.0000

Data Index: 459738 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.6580. Min Act: -0.0000

Data Index: 1356633 (C4 (Web Text))

Max Activating Token Index: 442