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

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

Neuron 4241 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.8649. Min Range: -10.8649

Max Act: 10.8649. Min Act: -0.0000

Data Index: 397249 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 10.8649. Min Range: -10.8649

Max Act: 10.6419. Min Act: -0.0000

Data Index: 2099 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 10.8649. Min Range: -10.8649

Max Act: 10.6708. Min Act: -0.0000

Data Index: 671743 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 10.8649. Min Range: -10.8649

Max Act: 10.6540. Min Act: -0.0000

Data Index: 434941 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 10.8649. Min Range: -10.8649

Max Act: 10.0396. Min Act: -0.0000

Data Index: 504184 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 10.8649. Min Range: -10.8649

Max Act: 10.4919. Min Act: -0.0000

Data Index: 93512 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 10.8649. Min Range: -10.8649

Max Act: 9.9032. Min Act: -0.0000

Data Index: 717267 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 10.8649. Min Range: -10.8649

Max Act: 9.8224. Min Act: -0.0000

Data Index: 813096 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 10.8649. Min Range: -10.8649

Max Act: 9.9226. Min Act: -0.0000

Data Index: 299178 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 10.8649. Min Range: -10.8649

Max Act: 9.6597. Min Act: -0.0000

Data Index: 1057494 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 10.8649. Min Range: -10.8649

Max Act: 9.8878. Min Act: -0.0000

Data Index: 210335 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 10.8649. Min Range: -10.8649

Max Act: 9.7831. Min Act: -0.0000

Data Index: 824831 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 10.8649. Min Range: -10.8649

Max Act: 9.7163. Min Act: -0.0000

Data Index: 938195 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 10.8649. Min Range: -10.8649

Max Act: 9.8445. Min Act: -0.0000

Data Index: 697255 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 10.8649. Min Range: -10.8649

Max Act: 9.6400. Min Act: -0.0000

Data Index: 524898 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 10.8649. Min Range: -10.8649

Max Act: 9.5996. Min Act: -0.0000

Data Index: 845297 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 10.8649. Min Range: -10.8649

Max Act: 9.7247. Min Act: -0.0000

Data Index: 768077 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 10.8649. Min Range: -10.8649

Max Act: 9.5668. Min Act: -0.0000

Data Index: 607952 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 10.8649. Min Range: -10.8649

Max Act: 9.0008. Min Act: -0.0000

Data Index: 257846 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 10.8649. Min Range: -10.8649

Max Act: 9.1338. Min Act: -0.0000

Data Index: 232754 (C4 (Web Text))

Max Activating Token Index: 740