Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3279 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.9858. Min Act: -0.0000

Data Index: 1252473 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 2.0072. Min Range: -2.0072

Max Act: 2.0031. Min Act: -0.0000

Data Index: 1002208 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.9652. Min Act: -0.0000

Data Index: 519272 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 2.0072. Min Range: -2.0072

Max Act: 2.0072. Min Act: -0.0000

Data Index: 105668 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.8493. Min Act: -0.0000

Data Index: 1240396 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.7732. Min Act: -0.0000

Data Index: 1011358 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.6360. Min Act: -0.0001

Data Index: 511787 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.5751. Min Act: -0.0000

Data Index: 386879 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.6343. Min Act: -0.0000

Data Index: 50889 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.4359. Min Act: -0.0000

Data Index: 59376 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.4651. Min Act: -0.0000

Data Index: 408877 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.3062. Min Act: -0.0000

Data Index: 1222639 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.4972. Min Act: -0.0001

Data Index: 147898 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.3768. Min Act: -0.0000

Data Index: 782657 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.3553. Min Act: -0.0000

Data Index: 924590 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.3487. Min Act: -0.0000

Data Index: 230064 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.3535. Min Act: -0.0000

Data Index: 218927 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.4035. Min Act: -0.0000

Data Index: 27209 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.3132. Min Act: -0.0000

Data Index: 1334234 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.2626. Min Act: -0.0000

Data Index: 1063573 (C4 (Web Text))

Max Activating Token Index: 324