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

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

Neuron 600 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0556. Min Act: -0.0002

Data Index: 992994 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0564. Min Act: -0.0002

Data Index: 185757 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0517. Min Act: -0.0002

Data Index: 896377 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1081169 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1251420 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1228233 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0461. Min Act: -0.0002

Data Index: 284125 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1324980 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0472. Min Act: -0.0002

Data Index: 500157 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0467. Min Act: -0.0002

Data Index: 27543 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1351130 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0463. Min Act: -0.0002

Data Index: 973133 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0449. Min Act: -0.0002

Data Index: 749454 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0421. Min Act: -0.0002

Data Index: 249745 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0418. Min Act: -0.0002

Data Index: 883298 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0411. Min Act: -0.0002

Data Index: 167461 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0393. Min Act: -0.0002

Data Index: 319927 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1027472 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0374. Min Act: -0.0002

Data Index: 1318665 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0379. Min Act: -0.0002

Data Index: 222611 (C4 (Web Text))

Max Activating Token Index: 113