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

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

Neuron 2213 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: 2.5308. Min Range: -2.5308

Max Act: 2.4422. Min Act: -0.0000

Data Index: 96178 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4320. Min Act: -0.0000

Data Index: 906971 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4157. Min Act: -0.0000

Data Index: 617022 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.3660. Min Act: -0.0000

Data Index: 548391 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4454. Min Act: -0.0000

Data Index: 1331944 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.5308. Min Act: -0.0000

Data Index: 952158 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.2620. Min Act: -0.0000

Data Index: 1156893 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.2511. Min Act: -0.0000

Data Index: 1013018 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.3613. Min Act: -0.0000

Data Index: 547241 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.3391. Min Act: -0.0000

Data Index: 440791 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.3136. Min Act: -0.0000

Data Index: 464902 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.3002. Min Act: -0.0000

Data Index: 539612 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.1740. Min Act: -0.0000

Data Index: 829683 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.3632. Min Act: -0.0000

Data Index: 686272 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.2201. Min Act: -0.0000

Data Index: 286248 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.2120. Min Act: -0.0000

Data Index: 455190 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.1964. Min Act: -0.0000

Data Index: 873011 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.1788. Min Act: -0.0000

Data Index: 661830 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.0317. Min Act: -0.0000

Data Index: 300255 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.0315. Min Act: -0.0000

Data Index: 484883 (C4 (Web Text))

Max Activating Token Index: 819