Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1689 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4603. Min Act: -0.0000

Data Index: 692680 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4355. Min Act: -0.0000

Data Index: 615878 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4558. Min Act: -0.0000

Data Index: 256570 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4047. Min Act: -0.0000

Data Index: 642010 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3953. Min Act: -0.0000

Data Index: 153466 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4154. Min Act: -0.0000

Data Index: 548355 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1340841 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3944. Min Act: -0.0000

Data Index: 132236 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3944. Min Act: -0.0000

Data Index: 1175753 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1210043 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3980. Min Act: -0.0000

Data Index: 429290 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4014. Min Act: -0.0000

Data Index: 753521 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1077169 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3588. Min Act: -0.0000

Data Index: 1224775 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3786. Min Act: -0.0000

Data Index: 1135034 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3788. Min Act: -0.0000

Data Index: 312117 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3412. Min Act: -0.0000

Data Index: 821817 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3744. Min Act: -0.0000

Data Index: 995094 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3496. Min Act: -0.0000

Data Index: 1054507 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3723. Min Act: -0.0000

Data Index: 906546 (C4 (Web Text))

Max Activating Token Index: 425