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

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

Neuron 4405 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: 0.0546. Min Range: -0.0546

Max Act: 0.0546. Min Act: -0.0002

Data Index: 915711 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0481. Min Act: -0.0002

Data Index: 193354 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0473. Min Act: -0.0002

Data Index: 976185 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0455. Min Act: -0.0002

Data Index: 268361 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1258041 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0444. Min Act: -0.0002

Data Index: 984426 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0431. Min Act: -0.0002

Data Index: 223994 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0435. Min Act: -0.0002

Data Index: 162005 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0429. Min Act: -0.0002

Data Index: 419814 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0429. Min Act: -0.0002

Data Index: 727910 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0429. Min Act: -0.0002

Data Index: 528546 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0427. Min Act: -0.0002

Data Index: 848850 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1257151 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0421. Min Act: -0.0002

Data Index: 451593 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1314828 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0409. Min Act: -0.0002

Data Index: 621864 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0405. Min Act: -0.0002

Data Index: 226457 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0408. Min Act: -0.0002

Data Index: 887656 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0400. Min Act: -0.0002

Data Index: 946330 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0390. Min Act: -0.0002

Data Index: 944756 (C4 (Web Text))

Max Activating Token Index: 507