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

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

Neuron 5144 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.6758. Min Act: -0.0000

Data Index: 1087851 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.2145. Min Act: -0.0000

Data Index: 1342946 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 1.6758. Min Range: -1.6758

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1016467 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 1.6758. Min Range: -1.6758

Max Act: 0.9840. Min Act: -0.0000

Data Index: 776513 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 1.6758. Min Range: -1.6758

Max Act: 0.8357. Min Act: 0.0000

Data Index: 1090777 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 1.6758. Min Range: -1.6758

Max Act: 0.7834. Min Act: -0.0000

Data Index: 998797 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 1.6758. Min Range: -1.6758

Max Act: 0.7189. Min Act: -0.0000

Data Index: 163218 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 1.6758. Min Range: -1.6758

Max Act: 0.7186. Min Act: -0.0000

Data Index: 1134039 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 1.6758. Min Range: -1.6758

Max Act: 0.7512. Min Act: -0.0000

Data Index: 975092 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 1.6758. Min Range: -1.6758

Max Act: 0.6878. Min Act: -0.0000

Data Index: 646253 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 1.6758. Min Range: -1.6758

Max Act: 0.6801. Min Act: -0.0000

Data Index: 332571 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 1.6758. Min Range: -1.6758

Max Act: 0.6807. Min Act: -0.0000

Data Index: 371049 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 1.6758. Min Range: -1.6758

Max Act: 0.6581. Min Act: -0.0000

Data Index: 119468 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 1.6758. Min Range: -1.6758

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1352640 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 1.6758. Min Range: -1.6758

Max Act: 0.6627. Min Act: -0.0000

Data Index: 618983 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 1.6758. Min Range: -1.6758

Max Act: 0.6382. Min Act: -0.0000

Data Index: 256783 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 1.6758. Min Range: -1.6758

Max Act: 0.6337. Min Act: -0.0000

Data Index: 322836 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 1.6758. Min Range: -1.6758

Max Act: 0.6294. Min Act: 0.0000

Data Index: 684897 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 1.6758. Min Range: -1.6758

Max Act: 0.6421. Min Act: 0.0001

Data Index: 270455 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 1.6758. Min Range: -1.6758

Max Act: 0.6271. Min Act: -0.0000

Data Index: 994567 (C4 (Web Text))

Max Activating Token Index: 97