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

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

Neuron 5850 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3249. Min Range: -2.3249

Max Act: 2.3249. Min Act: -0.0000

Data Index: 225529 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 2.3249. Min Range: -2.3249

Max Act: 1.8771. Min Act: -0.0000

Data Index: 819293 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 2.3249. Min Range: -2.3249

Max Act: 1.8453. Min Act: -0.0000

Data Index: 118263 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 2.3249. Min Range: -2.3249

Max Act: 1.7877. Min Act: -0.0000

Data Index: 1193674 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 2.3249. Min Range: -2.3249

Max Act: 1.8515. Min Act: -0.0000

Data Index: 1264340 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 2.3249. Min Range: -2.3249

Max Act: 1.7374. Min Act: -0.0000

Data Index: 345354 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 2.3249. Min Range: -2.3249

Max Act: 1.7258. Min Act: -0.0000

Data Index: 165053 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 2.3249. Min Range: -2.3249

Max Act: 1.6510. Min Act: -0.0000

Data Index: 1304845 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 2.3249. Min Range: -2.3249

Max Act: 1.6854. Min Act: -0.0000

Data Index: 1045881 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 2.3249. Min Range: -2.3249

Max Act: 1.6905. Min Act: -0.0000

Data Index: 1246322 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 2.3249. Min Range: -2.3249

Max Act: 1.6637. Min Act: -0.0000

Data Index: 338305 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 2.3249. Min Range: -2.3249

Max Act: 1.6564. Min Act: -0.0000

Data Index: 733270 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 2.3249. Min Range: -2.3249

Max Act: 1.6187. Min Act: -0.0000

Data Index: 628349 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 2.3249. Min Range: -2.3249

Max Act: 1.6873. Min Act: -0.0000

Data Index: 511652 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 2.3249. Min Range: -2.3249

Max Act: 1.4897. Min Act: -0.0000

Data Index: 47652 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 2.3249. Min Range: -2.3249

Max Act: 1.5494. Min Act: -0.0000

Data Index: 1162252 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 2.3249. Min Range: -2.3249

Max Act: 1.5382. Min Act: -0.0000

Data Index: 944800 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 2.3249. Min Range: -2.3249

Max Act: 1.6239. Min Act: -0.0000

Data Index: 981221 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 2.3249. Min Range: -2.3249

Max Act: 1.5256. Min Act: -0.0000

Data Index: 971234 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 2.3249. Min Range: -2.3249

Max Act: 1.6087. Min Act: -0.0000

Data Index: 1119839 (C4 (Web Text))

Max Activating Token Index: 142