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

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

Neuron 2310 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: 2.3468. Min Range: -2.3468

Max Act: 2.3468. Min Act: -0.0000

Data Index: 1337590 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 2.3468. Min Range: -2.3468

Max Act: 2.0899. Min Act: -0.0000

Data Index: 776336 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 2.3468. Min Range: -2.3468

Max Act: 1.9227. Min Act: -0.0000

Data Index: 366048 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 2.3468. Min Range: -2.3468

Max Act: 1.8036. Min Act: -0.0000

Data Index: 36989 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 2.3468. Min Range: -2.3468

Max Act: 1.7479. Min Act: -0.0000

Data Index: 1092582 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 2.3468. Min Range: -2.3468

Max Act: 1.7015. Min Act: -0.0000

Data Index: 491230 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 2.3468. Min Range: -2.3468

Max Act: 1.6468. Min Act: -0.0000

Data Index: 591139 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 2.3468. Min Range: -2.3468

Max Act: 1.6460. Min Act: -0.0000

Data Index: 846850 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 2.3468. Min Range: -2.3468

Max Act: 1.6363. Min Act: -0.0000

Data Index: 1304515 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 2.3468. Min Range: -2.3468

Max Act: 1.6376. Min Act: -0.0000

Data Index: 1289041 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 2.3468. Min Range: -2.3468

Max Act: 1.6051. Min Act: -0.0000

Data Index: 443530 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 2.3468. Min Range: -2.3468

Max Act: 1.5986. Min Act: -0.0000

Data Index: 1516160 (Python Code)

Max Activating Token Index: 84

Text #12

Max Range: 2.3468. Min Range: -2.3468

Max Act: 1.6719. Min Act: -0.0000

Data Index: 70039 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 2.3468. Min Range: -2.3468

Max Act: 1.6746. Min Act: -0.0000

Data Index: 981413 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 2.3468. Min Range: -2.3468

Max Act: 1.5709. Min Act: -0.0000

Data Index: 1330019 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 2.3468. Min Range: -2.3468

Max Act: 1.6294. Min Act: -0.0000

Data Index: 1167266 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 2.3468. Min Range: -2.3468

Max Act: 1.5291. Min Act: -0.0000

Data Index: 658751 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 2.3468. Min Range: -2.3468

Max Act: 1.4953. Min Act: -0.0000

Data Index: 101395 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 2.3468. Min Range: -2.3468

Max Act: 1.4921. Min Act: -0.0000

Data Index: 766729 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 2.3468. Min Range: -2.3468

Max Act: 1.4902. Min Act: -0.0000

Data Index: 768001 (C4 (Web Text))

Max Activating Token Index: 288