Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2298 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.7408. Min Act: -0.0000

Data Index: 1013351 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.6207. Min Act: -0.0000

Data Index: 145799 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.4378. Min Act: -0.0000

Data Index: 278515 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.6096. Min Act: -0.0000

Data Index: 183470 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.5112. Min Act: -0.0000

Data Index: 807201 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.4251. Min Act: -0.0000

Data Index: 631926 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.5873. Min Act: -0.0000

Data Index: 1302538 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.4708. Min Act: -0.0000

Data Index: 1033635 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.4718. Min Act: -0.0000

Data Index: 1035629 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.4551. Min Act: -0.0000

Data Index: 1249241 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.3719. Min Act: -0.0000

Data Index: 133925 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.4508. Min Act: -0.0000

Data Index: 671147 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.3586. Min Act: -0.0000

Data Index: 680627 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.4390. Min Act: -0.0000

Data Index: 1124920 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.5076. Min Act: -0.0000

Data Index: 694429 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.3379. Min Act: -0.0000

Data Index: 1118430 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.4708. Min Act: -0.0000

Data Index: 839023 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.3810. Min Act: -0.0000

Data Index: 569414 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.3763. Min Act: -0.0001

Data Index: 1266525 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 1.7408. Min Range: -1.7408

Max Act: 1.3373. Min Act: -0.0001

Data Index: 665395 (C4 (Web Text))

Max Activating Token Index: 854