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

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

Neuron 4579 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5090. Min Range: -1.5090

Max Act: 1.5090. Min Act: -0.0000

Data Index: 402277 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 1.5090. Min Range: -1.5090

Max Act: 1.2712. Min Act: -0.0000

Data Index: 306766 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 1.5090. Min Range: -1.5090

Max Act: 1.0310. Min Act: -0.0000

Data Index: 1223553 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 1.5090. Min Range: -1.5090

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1219658 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 1.5090. Min Range: -1.5090

Max Act: 0.8278. Min Act: -0.0000

Data Index: 928310 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 1.5090. Min Range: -1.5090

Max Act: 0.7692. Min Act: -0.0000

Data Index: 663593 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 1.5090. Min Range: -1.5090

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1195055 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 1.5090. Min Range: -1.5090

Max Act: 0.8157. Min Act: -0.0000

Data Index: 40474 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 1.5090. Min Range: -1.5090

Max Act: 0.8253. Min Act: -0.0000

Data Index: 268272 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 1.5090. Min Range: -1.5090

Max Act: 0.7477. Min Act: -0.0000

Data Index: 382232 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 1.5090. Min Range: -1.5090

Max Act: 0.7904. Min Act: -0.0000

Data Index: 781785 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 1.5090. Min Range: -1.5090

Max Act: 0.7157. Min Act: -0.0000

Data Index: 514213 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 1.5090. Min Range: -1.5090

Max Act: 0.7575. Min Act: -0.0000

Data Index: 53402 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 1.5090. Min Range: -1.5090

Max Act: 0.7430. Min Act: -0.0000

Data Index: 1199263 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 1.5090. Min Range: -1.5090

Max Act: 0.7432. Min Act: -0.0000

Data Index: 348026 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 1.5090. Min Range: -1.5090

Max Act: 0.7714. Min Act: -0.0000

Data Index: 56627 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 1.5090. Min Range: -1.5090

Max Act: 0.7349. Min Act: -0.0000

Data Index: 441859 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 1.5090. Min Range: -1.5090

Max Act: 0.7241. Min Act: -0.0000

Data Index: 1098475 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 1.5090. Min Range: -1.5090

Max Act: 0.7471. Min Act: -0.0000

Data Index: 551132 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 1.5090. Min Range: -1.5090

Max Act: 0.6526. Min Act: -0.0000

Data Index: 451932 (C4 (Web Text))

Max Activating Token Index: 778