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

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

Neuron 505 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1303. Min Range: -1.1303

Max Act: 1.1054. Min Act: -0.0000

Data Index: 1333896 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 1.1303. Min Range: -1.1303

Max Act: 1.1303. Min Act: -0.0000

Data Index: 239053 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9039. Min Act: -0.0000

Data Index: 223901 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 1.1303. Min Range: -1.1303

Max Act: 1.0029. Min Act: -0.0000

Data Index: 724160 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9399. Min Act: -0.0000

Data Index: 824668 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9989. Min Act: -0.0000

Data Index: 228789 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9848. Min Act: -0.0000

Data Index: 704658 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9467. Min Act: -0.0000

Data Index: 639751 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8856. Min Act: -0.0000

Data Index: 634152 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9335. Min Act: -0.0000

Data Index: 1358505 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8977. Min Act: -0.0000

Data Index: 810300 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8972. Min Act: -0.0000

Data Index: 1045398 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8811. Min Act: -0.0000

Data Index: 138932 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8844. Min Act: -0.0000

Data Index: 632306 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8743. Min Act: -0.0000

Data Index: 201252 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1225990 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9492. Min Act: -0.0000

Data Index: 908053 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8363. Min Act: -0.0000

Data Index: 391555 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8939. Min Act: -0.0000

Data Index: 455880 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8857. Min Act: -0.0000

Data Index: 701506 (C4 (Web Text))

Max Activating Token Index: 852