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

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

Neuron 820 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2300. Min Act: -0.0000

Data Index: 837453 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2095. Min Act: -0.0000

Data Index: 1103625 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2531. Min Act: -0.0001

Data Index: 143138 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2269. Min Act: -0.0000

Data Index: 396615 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2178. Min Act: -0.0000

Data Index: 286983 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2256. Min Act: -0.0000

Data Index: 450213 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2020. Min Act: -0.0001

Data Index: 233056 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2212. Min Act: -0.0000

Data Index: 164850 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2087. Min Act: -0.0001

Data Index: 137569 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1308812 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1995. Min Act: -0.0000

Data Index: 593347 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2003. Min Act: -0.0001

Data Index: 874929 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2076. Min Act: -0.0000

Data Index: 512412 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1002537 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2031. Min Act: -0.0001

Data Index: 991771 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2027. Min Act: -0.0000

Data Index: 930736 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1844. Min Act: -0.0000

Data Index: 423295 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1993. Min Act: -0.0000

Data Index: 506025 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1993. Min Act: -0.0001

Data Index: 944783 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1047199 (C4 (Web Text))

Max Activating Token Index: 247