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

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

Neuron 2256 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7339. Min Range: -2.7339

Max Act: 2.7339. Min Act: -0.0000

Data Index: 42051 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 2.7339. Min Range: -2.7339

Max Act: 2.4838. Min Act: -0.0000

Data Index: 1310444 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 2.7339. Min Range: -2.7339

Max Act: 2.2582. Min Act: -0.0000

Data Index: 579402 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 2.7339. Min Range: -2.7339

Max Act: 1.8102. Min Act: -0.0000

Data Index: 1328200 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 2.7339. Min Range: -2.7339

Max Act: 1.7831. Min Act: -0.0000

Data Index: 339026 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 2.7339. Min Range: -2.7339

Max Act: 1.6759. Min Act: -0.0000

Data Index: 282340 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 2.7339. Min Range: -2.7339

Max Act: 1.6148. Min Act: -0.0000

Data Index: 828582 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 2.7339. Min Range: -2.7339

Max Act: 1.5669. Min Act: -0.0000

Data Index: 1150863 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 2.7339. Min Range: -2.7339

Max Act: 1.6653. Min Act: -0.0000

Data Index: 1023193 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 2.7339. Min Range: -2.7339

Max Act: 1.4884. Min Act: -0.0000

Data Index: 647410 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 2.7339. Min Range: -2.7339

Max Act: 1.4959. Min Act: -0.0000

Data Index: 530989 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 2.7339. Min Range: -2.7339

Max Act: 1.4302. Min Act: -0.0000

Data Index: 724013 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 2.7339. Min Range: -2.7339

Max Act: 1.2623. Min Act: -0.0000

Data Index: 544453 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 2.7339. Min Range: -2.7339

Max Act: 1.4173. Min Act: -0.0000

Data Index: 169997 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 2.7339. Min Range: -2.7339

Max Act: 1.4093. Min Act: -0.0000

Data Index: 599058 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 2.7339. Min Range: -2.7339

Max Act: 1.2520. Min Act: -0.0000

Data Index: 228413 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 2.7339. Min Range: -2.7339

Max Act: 1.3144. Min Act: -0.0000

Data Index: 494394 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 2.7339. Min Range: -2.7339

Max Act: 1.3812. Min Act: -0.0000

Data Index: 294680 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 2.7339. Min Range: -2.7339

Max Act: 1.4692. Min Act: -0.0000

Data Index: 103805 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 2.7339. Min Range: -2.7339

Max Act: 1.5176. Min Act: -0.0000

Data Index: 451751 (C4 (Web Text))

Max Activating Token Index: 529