Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2535 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.6738. Min Act: -0.0000

Data Index: 597167 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.6548. Min Act: -0.0001

Data Index: 617995 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.6863. Min Act: -0.0001

Data Index: 1056227 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.6460. Min Act: -0.0000

Data Index: 643807 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.6430. Min Act: -0.0000

Data Index: 695359 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.5813. Min Act: -0.0001

Data Index: 1043762 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.6145. Min Act: -0.0001

Data Index: 382603 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.6465. Min Act: -0.0001

Data Index: 86827 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.6199. Min Act: -0.0000

Data Index: 861037 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.5584. Min Act: -0.0001

Data Index: 1189662 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.5744. Min Act: -0.0001

Data Index: 1145464 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.6036. Min Act: -0.0000

Data Index: 59838 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.5815. Min Act: -0.0000

Data Index: 462931 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.5627. Min Act: -0.0001

Data Index: 320219 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.5751. Min Act: -0.0001

Data Index: 979974 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.5098. Min Act: -0.0001

Data Index: 65495 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.5974. Min Act: -0.0000

Data Index: 787334 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.5867. Min Act: -0.0000

Data Index: 1007569 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.5456. Min Act: -0.0001

Data Index: 145395 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.5393. Min Act: -0.0000

Data Index: 1198882 (C4 (Web Text))

Max Activating Token Index: 661