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

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

Neuron 4078 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.4835. Min Act: -0.0000

Data Index: 1337072 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.4959. Min Act: -0.0000

Data Index: 743438 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.4064. Min Act: -0.0000

Data Index: 599533 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.4173. Min Act: -0.0000

Data Index: 704292 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3837. Min Act: -0.0000

Data Index: 870611 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1120856 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1205473 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3306. Min Act: -0.0000

Data Index: 529944 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3271. Min Act: -0.0000

Data Index: 988448 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3346. Min Act: -0.0000

Data Index: 459505 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3698. Min Act: -0.0000

Data Index: 314523 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3555. Min Act: -0.0000

Data Index: 953098 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3519. Min Act: -0.0000

Data Index: 172916 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3469. Min Act: -0.0000

Data Index: 922211 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3547. Min Act: -0.0000

Data Index: 272965 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3400. Min Act: -0.0000

Data Index: 660062 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1005950 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3494. Min Act: -0.0000

Data Index: 1295158 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3370. Min Act: -0.0000

Data Index: 942837 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 0.4959. Min Range: -0.4959

Max Act: 0.3323. Min Act: -0.0000

Data Index: 1132302 (C4 (Web Text))

Max Activating Token Index: 525