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

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

Neuron 4410 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.6711. Min Act: -0.0000

Data Index: 112987 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.4265. Min Act: -0.0000

Data Index: 54841 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.5109. Min Act: -0.0001

Data Index: 12279 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.4386. Min Act: -0.0000

Data Index: 270431 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.3304. Min Act: -0.0000

Data Index: 1165536 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.4178. Min Act: -0.0000

Data Index: 893408 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.4045. Min Act: -0.0000

Data Index: 136293 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.3866. Min Act: -0.0001

Data Index: 1028582 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.3558. Min Act: -0.0000

Data Index: 1085274 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.3272. Min Act: -0.0000

Data Index: 457907 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.2902. Min Act: -0.0000

Data Index: 1175767 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.4059. Min Act: -0.0000

Data Index: 606833 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.2360. Min Act: -0.0000

Data Index: 32559 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.2170. Min Act: -0.0001

Data Index: 24223 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.2111. Min Act: -0.0000

Data Index: 928555 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.3054. Min Act: -0.0000

Data Index: 1171366 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.1989. Min Act: -0.0000

Data Index: 1350260 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.1806. Min Act: -0.0000

Data Index: 442993 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.0801. Min Act: -0.0000

Data Index: 743186 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 2.6711. Min Range: -2.6711

Max Act: 2.1714. Min Act: -0.0000

Data Index: 86790 (C4 (Web Text))

Max Activating Token Index: 185