Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 256 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0006

Data Index: 373980 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0301. Min Act: -0.0006

Data Index: 1199840 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0301. Min Act: -0.0006

Data Index: 1053522 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0300. Min Act: -0.0006

Data Index: 624015 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0294. Min Act: -0.0006

Data Index: 681736 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0294. Min Act: -0.0006

Data Index: 666737 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0300. Min Act: -0.0006

Data Index: 153305 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0290. Min Act: -0.0006

Data Index: 1207034 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0297. Min Act: -0.0006

Data Index: 277245 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0297. Min Act: -0.0005

Data Index: 53599 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0290. Min Act: -0.0006

Data Index: 246368 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0284. Min Act: -0.0006

Data Index: 673163 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0284. Min Act: -0.0006

Data Index: 34538 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0282. Min Act: -0.0006

Data Index: 840726 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0270. Min Act: -0.0006

Data Index: 1217929 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0280. Min Act: -0.0006

Data Index: 1226383 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0279. Min Act: -0.0006

Data Index: 279805 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0279. Min Act: -0.0006

Data Index: 253900 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0279. Min Act: -0.0006

Data Index: 1017896 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0285. Min Act: -0.0006

Data Index: 747998 (C4 (Web Text))

Max Activating Token Index: 529