Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2159 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.8258. Min Act: -0.0001

Data Index: 1296604 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7526. Min Act: -0.0001

Data Index: 826311 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7678. Min Act: -0.0001

Data Index: 1250136 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7581. Min Act: -0.0001

Data Index: 1346267 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6828. Min Act: -0.0001

Data Index: 966927 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6526. Min Act: -0.0002

Data Index: 987150 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6713. Min Act: -0.0001

Data Index: 38070 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6205. Min Act: -0.0001

Data Index: 639442 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6819. Min Act: -0.0001

Data Index: 1319318 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.5936. Min Act: -0.0002

Data Index: 896122 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.5989. Min Act: -0.0002

Data Index: 798167 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6320. Min Act: -0.0002

Data Index: 666406 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6301. Min Act: -0.0002

Data Index: 1158649 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.5956. Min Act: -0.0002

Data Index: 1071309 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6590. Min Act: -0.0002

Data Index: 71293 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6217. Min Act: -0.0002

Data Index: 522982 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6419. Min Act: -0.0002

Data Index: 1267454 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6179. Min Act: -0.0002

Data Index: 85078 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6354. Min Act: -0.0001

Data Index: 455802 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6529. Min Act: -0.0001

Data Index: 451614 (C4 (Web Text))

Max Activating Token Index: 215