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

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

Neuron 1394 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.2239. Min Act: -0.0000

Data Index: 423147 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1316. Min Act: -0.0000

Data Index: 834899 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1338. Min Act: -0.0000

Data Index: 1003145 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1081. Min Act: -0.0000

Data Index: 1191670 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1087. Min Act: -0.0000

Data Index: 7444 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1065. Min Act: -0.0000

Data Index: 856908 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.0955. Min Act: -0.0000

Data Index: 496730 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1044. Min Act: -0.0000

Data Index: 634834 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1001. Min Act: -0.0000

Data Index: 34041 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.0962. Min Act: -0.0000

Data Index: 77780 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.0890. Min Act: -0.0000

Data Index: 984322 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.0953. Min Act: -0.0000

Data Index: 860117 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.0944. Min Act: -0.0000

Data Index: 587051 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.0836. Min Act: -0.0000

Data Index: 1105440 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.0949. Min Act: -0.0000

Data Index: 859909 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.0912. Min Act: -0.0000

Data Index: 331316 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1045. Min Act: -0.0000

Data Index: 1151081 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.0940. Min Act: -0.0000

Data Index: 198402 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.0927. Min Act: -0.0000

Data Index: 12390 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.0915. Min Act: -0.0000

Data Index: 111054 (C4 (Web Text))

Max Activating Token Index: 473