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

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

Neuron 5690 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2235. Min Act: -0.0000

Data Index: 35377 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1064135 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1554. Min Act: -0.0000

Data Index: 669718 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1267. Min Act: -0.0000

Data Index: 1236875 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1210. Min Act: -0.0000

Data Index: 402813 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1179. Min Act: -0.0000

Data Index: 673526 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1128. Min Act: -0.0000

Data Index: 862897 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1102. Min Act: -0.0000

Data Index: 978937 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1038. Min Act: -0.0000

Data Index: 864598 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1164622 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1302271 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1523 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1077. Min Act: -0.0000

Data Index: 168937 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0935. Min Act: -0.0000

Data Index: 90271 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1003. Min Act: -0.0000

Data Index: 498382 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1205634 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0972. Min Act: -0.0000

Data Index: 965685 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0971. Min Act: -0.0000

Data Index: 662634 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0900. Min Act: -0.0000

Data Index: 441759 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1333804 (C4 (Web Text))

Max Activating Token Index: 519