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

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

Neuron 2395 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0229. Min Range: -1.0229

Max Act: 1.0229. Min Act: -0.0000

Data Index: 604619 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.9895. Min Act: -0.0000

Data Index: 1162509 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7931. Min Act: -0.0000

Data Index: 551998 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1060878 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7916. Min Act: -0.0000

Data Index: 1214569 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.6995. Min Act: -0.0000

Data Index: 459503 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7156. Min Act: -0.0000

Data Index: 1345548 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7159. Min Act: -0.0000

Data Index: 714290 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1328727 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1196075 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.6992. Min Act: -0.0000

Data Index: 144609 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7117. Min Act: -0.0000

Data Index: 1048594 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1174840 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7045. Min Act: -0.0000

Data Index: 199993 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1336145 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.7077. Min Act: -0.0000

Data Index: 436837 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.6831. Min Act: -0.0000

Data Index: 371083 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.6784. Min Act: -0.0000

Data Index: 1130893 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1137787 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 1.0229. Min Range: -1.0229

Max Act: 0.6527. Min Act: -0.0000

Data Index: 891548 (C4 (Web Text))

Max Activating Token Index: 1006