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

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

Neuron 4163 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1312. Min Act: -0.0002

Data Index: 1156836 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1285. Min Act: -0.0002

Data Index: 791250 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1074. Min Act: -0.0002

Data Index: 1041170 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1291. Min Act: -0.0002

Data Index: 2770 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1231. Min Act: -0.0002

Data Index: 483499 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1200. Min Act: -0.0002

Data Index: 1204890 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1159. Min Act: -0.0002

Data Index: 1249078 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1043. Min Act: -0.0002

Data Index: 432866 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0983. Min Act: -0.0002

Data Index: 21475 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0986. Min Act: -0.0002

Data Index: 115511 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1031. Min Act: -0.0002

Data Index: 1167422 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1260. Min Act: -0.0002

Data Index: 1342213 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0888. Min Act: -0.0002

Data Index: 858949 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1122. Min Act: -0.0002

Data Index: 1242955 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0992. Min Act: -0.0002

Data Index: 818318 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1001. Min Act: -0.0002

Data Index: 862270 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1087. Min Act: -0.0002

Data Index: 1234501 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0992. Min Act: -0.0002

Data Index: 65746 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1037. Min Act: -0.0002

Data Index: 108094 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0913. Min Act: -0.0002

Data Index: 326383 (C4 (Web Text))

Max Activating Token Index: 193