Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1121 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.2259. Min Act: -0.0001

Data Index: 158785 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.2070. Min Act: -0.0001

Data Index: 501938 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.2109. Min Act: -0.0001

Data Index: 1329445 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.2146. Min Act: -0.0001

Data Index: 928341 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1872. Min Act: -0.0001

Data Index: 735832 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1990. Min Act: -0.0001

Data Index: 467657 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1068027 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1900. Min Act: -0.0001

Data Index: 763414 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1960. Min Act: -0.0001

Data Index: 170002 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.2024. Min Act: -0.0001

Data Index: 259065 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1927. Min Act: -0.0001

Data Index: 941991 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.2082. Min Act: -0.0001

Data Index: 677662 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.2006. Min Act: -0.0001

Data Index: 1291249 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1870. Min Act: -0.0001

Data Index: 106285 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1929. Min Act: -0.0001

Data Index: 648222 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1814. Min Act: -0.0001

Data Index: 212734 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1865. Min Act: -0.0001

Data Index: 782719 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1910. Min Act: -0.0001

Data Index: 1151048 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1852. Min Act: -0.0001

Data Index: 118178 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1772. Min Act: -0.0001

Data Index: 1080358 (C4 (Web Text))

Max Activating Token Index: 413