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

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

Neuron 4877 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4680. Min Act: -0.0000

Data Index: 123911 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1191809 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3507. Min Act: -0.0000

Data Index: 172619 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3470. Min Act: -0.0000

Data Index: 870888 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.2727. Min Act: -0.0000

Data Index: 142425 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.2682. Min Act: -0.0000

Data Index: 187925 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.2804. Min Act: -0.0000

Data Index: 68374 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.2471. Min Act: -0.0000

Data Index: 777158 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.2469. Min Act: -0.0000

Data Index: 955181 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.2225. Min Act: -0.0000

Data Index: 460035 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1122936 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.2524. Min Act: -0.0000

Data Index: 1190217 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1365276 (Python Code)

Max Activating Token Index: 774

Text #13

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.2121. Min Act: -0.0000

Data Index: 255962 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1076452 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.2098. Min Act: -0.0000

Data Index: 769441 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.2099. Min Act: -0.0000

Data Index: 766498 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.2089. Min Act: -0.0000

Data Index: 604982 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.1909. Min Act: -0.0000

Data Index: 644031 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.1948. Min Act: -0.0000

Data Index: 114542 (C4 (Web Text))

Max Activating Token Index: 639