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

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

Neuron 5495 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.5991. Min Range: -4.5991

Max Act: 4.5991. Min Act: -0.0000

Data Index: 592 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 4.5991. Min Range: -4.5991

Max Act: 4.1385. Min Act: -0.0000

Data Index: 495739 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 4.5991. Min Range: -4.5991

Max Act: 3.9896. Min Act: -0.0000

Data Index: 1167173 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 4.5991. Min Range: -4.5991

Max Act: 3.5815. Min Act: -0.0000

Data Index: 1250222 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 4.5991. Min Range: -4.5991

Max Act: 3.5263. Min Act: -0.0000

Data Index: 501711 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 4.5991. Min Range: -4.5991

Max Act: 3.5340. Min Act: -0.0000

Data Index: 771854 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 4.5991. Min Range: -4.5991

Max Act: 3.5543. Min Act: -0.0000

Data Index: 888997 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 4.5991. Min Range: -4.5991

Max Act: 3.2142. Min Act: -0.0000

Data Index: 835999 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 4.5991. Min Range: -4.5991

Max Act: 3.2933. Min Act: -0.0000

Data Index: 1066757 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 4.5991. Min Range: -4.5991

Max Act: 3.2790. Min Act: -0.0000

Data Index: 18732 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 4.5991. Min Range: -4.5991

Max Act: 3.0911. Min Act: -0.0000

Data Index: 329034 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 4.5991. Min Range: -4.5991

Max Act: 2.8705. Min Act: -0.0000

Data Index: 711390 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 4.5991. Min Range: -4.5991

Max Act: 3.1961. Min Act: -0.0000

Data Index: 639053 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 4.5991. Min Range: -4.5991

Max Act: 2.9982. Min Act: -0.0000

Data Index: 438121 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 4.5991. Min Range: -4.5991

Max Act: 3.0028. Min Act: -0.0000

Data Index: 999836 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 4.5991. Min Range: -4.5991

Max Act: 3.0609. Min Act: -0.0000

Data Index: 769796 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 4.5991. Min Range: -4.5991

Max Act: 2.8931. Min Act: -0.0000

Data Index: 85576 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 4.5991. Min Range: -4.5991

Max Act: 2.8888. Min Act: -0.0000

Data Index: 1001026 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 4.5991. Min Range: -4.5991

Max Act: 3.2228. Min Act: -0.0000

Data Index: 1155172 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 4.5991. Min Range: -4.5991

Max Act: 3.0388. Min Act: -0.0000

Data Index: 82214 (C4 (Web Text))

Max Activating Token Index: 310