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

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

Neuron 4994 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.5149. Min Act: -0.0000

Data Index: 493956 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.5492. Min Act: -0.0000

Data Index: 991219 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.1782. Min Act: -0.0000

Data Index: 1134883 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.0326. Min Act: -0.0000

Data Index: 864052 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.1455. Min Act: -0.0000

Data Index: 755814 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.0340. Min Act: -0.0000

Data Index: 46371 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.0617. Min Act: -0.0000

Data Index: 243838 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.0417. Min Act: -0.0000

Data Index: 729728 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.0565. Min Act: -0.0000

Data Index: 958989 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 1.5492. Min Range: -1.5492

Max Act: 0.9578. Min Act: -0.0000

Data Index: 722638 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.0181. Min Act: -0.0000

Data Index: 1174259 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.0047. Min Act: -0.0000

Data Index: 1024960 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.0034. Min Act: -0.0000

Data Index: 662150 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1203682 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 1.5492. Min Range: -1.5492

Max Act: 0.9307. Min Act: -0.0000

Data Index: 177602 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.0031. Min Act: -0.0000

Data Index: 197859 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 1.5492. Min Range: -1.5492

Max Act: 0.9891. Min Act: -0.0000

Data Index: 1084610 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 1.5492. Min Range: -1.5492

Max Act: 0.9577. Min Act: -0.0000

Data Index: 189885 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.0077. Min Act: -0.0000

Data Index: 79369 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 1.5492. Min Range: -1.5492

Max Act: 0.8488. Min Act: -0.0000

Data Index: 1090698 (C4 (Web Text))

Max Activating Token Index: 501