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

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

Neuron 760 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.6759. Min Act: -0.0000

Data Index: 510244 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.6024. Min Act: -0.0000

Data Index: 199554 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.6241. Min Act: -0.0000

Data Index: 726111 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.6032. Min Act: -0.0001

Data Index: 1273189 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5331. Min Act: -0.0001

Data Index: 871257 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1198248 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5514. Min Act: -0.0001

Data Index: 508879 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.4943. Min Act: -0.0001

Data Index: 381042 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5124. Min Act: -0.0001

Data Index: 818307 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5053. Min Act: -0.0000

Data Index: 716055 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1332957 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.4479. Min Act: -0.0000

Data Index: 509441 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.4559. Min Act: -0.0001

Data Index: 716628 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.4648. Min Act: -0.0000

Data Index: 134468 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.4430. Min Act: -0.0000

Data Index: 336226 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.4530. Min Act: -0.0000

Data Index: 137235 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1226071 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.4355. Min Act: -0.0001

Data Index: 434739 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.4322. Min Act: -0.0000

Data Index: 710272 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.4303. Min Act: -0.0000

Data Index: 784011 (C4 (Web Text))

Max Activating Token Index: 91