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

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

Neuron 310 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: 0.2242. Min Range: -0.2242

Max Act: 0.2242. Min Act: -0.0000

Data Index: 708163 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.2184. Min Act: -0.0000

Data Index: 1167881 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.2140. Min Act: -0.0000

Data Index: 302124 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.2132. Min Act: -0.0000

Data Index: 793708 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.2024. Min Act: -0.0000

Data Index: 792158 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1967. Min Act: -0.0000

Data Index: 74759 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1225399 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1892. Min Act: -0.0000

Data Index: 520627 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1885. Min Act: -0.0000

Data Index: 748757 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1882. Min Act: -0.0001

Data Index: 871407 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1826. Min Act: -0.0001

Data Index: 60353 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1745. Min Act: -0.0001

Data Index: 951730 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1776. Min Act: -0.0000

Data Index: 1276353 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1815. Min Act: -0.0000

Data Index: 1174479 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1746. Min Act: -0.0000

Data Index: 1171389 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1738. Min Act: 0.0000

Data Index: 629555 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1665. Min Act: 0.0000

Data Index: 1017027 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1715. Min Act: -0.0001

Data Index: 986333 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1066640 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1684. Min Act: -0.0000

Data Index: 10100 (C4 (Web Text))

Max Activating Token Index: 390