Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6000 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.6327. Min Act: -0.0000

Data Index: 418566 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.6408. Min Act: -0.0000

Data Index: 783800 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1151943 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.6017. Min Act: -0.0000

Data Index: 699883 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.6328. Min Act: -0.0000

Data Index: 787933 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.6209. Min Act: -0.0000

Data Index: 244961 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.6090. Min Act: -0.0000

Data Index: 1288600 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.6291. Min Act: -0.0000

Data Index: 147372 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.6309. Min Act: -0.0000

Data Index: 647034 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.6088. Min Act: -0.0000

Data Index: 286276 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.6257. Min Act: -0.0000

Data Index: 523610 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1246444 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.6119. Min Act: -0.0000

Data Index: 945080 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.5739. Min Act: -0.0000

Data Index: 338528 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1106663 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.6341. Min Act: -0.0000

Data Index: 76347 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1313219 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.6222. Min Act: -0.0000

Data Index: 498126 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.5845. Min Act: -0.0000

Data Index: 874329 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.5803. Min Act: -0.0000

Data Index: 1219131 (C4 (Web Text))

Max Activating Token Index: 866