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

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

Neuron 5980 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.6835. Min Act: -0.0000

Data Index: 723656 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1243132 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.6111. Min Act: -0.0000

Data Index: 1349994 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.5582. Min Act: -0.0000

Data Index: 327002 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.5293. Min Act: -0.0000

Data Index: 638191 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.5291. Min Act: -0.0000

Data Index: 508891 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.5246. Min Act: -0.0000

Data Index: 223269 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1241484 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4859. Min Act: -0.0000

Data Index: 161421 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4972. Min Act: -0.0000

Data Index: 672216 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4635. Min Act: -0.0000

Data Index: 631340 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1391593 (Python Code)

Max Activating Token Index: 509

Text #12

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4396. Min Act: -0.0000

Data Index: 150028 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.3860. Min Act: -0.0000

Data Index: 311543 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4292. Min Act: -0.0000

Data Index: 379647 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4242. Min Act: -0.0000

Data Index: 580527 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4421. Min Act: -0.0000

Data Index: 810954 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4078. Min Act: -0.0000

Data Index: 746321 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.3982. Min Act: -0.0000

Data Index: 204215 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.3739. Min Act: -0.0000

Data Index: 217937 (C4 (Web Text))

Max Activating Token Index: 187