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

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

Neuron 55 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6704. Min Range: -2.6704

Max Act: 2.6704. Min Act: -0.0000

Data Index: 124669 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.9260. Min Act: -0.0000

Data Index: 914093 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 2.6704. Min Range: -2.6704

Max Act: 2.3312. Min Act: -0.0000

Data Index: 912233 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 2.6704. Min Range: -2.6704

Max Act: 2.0998. Min Act: -0.0000

Data Index: 742954 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.9939. Min Act: -0.0000

Data Index: 668557 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.9794. Min Act: -0.0000

Data Index: 695234 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.8526. Min Act: 0.0000

Data Index: 1330133 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.8138. Min Act: -0.0000

Data Index: 225265 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.9301. Min Act: -0.0000

Data Index: 232838 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.9090. Min Act: -0.0000

Data Index: 957738 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.8175. Min Act: -0.0000

Data Index: 489450 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 2.6704. Min Range: -2.6704

Max Act: 2.0141. Min Act: -0.0000

Data Index: 823577 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.8044. Min Act: -0.0000

Data Index: 794462 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.8420. Min Act: -0.0000

Data Index: 584063 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.7057. Min Act: -0.0000

Data Index: 1569709 (Python Code)

Max Activating Token Index: 805

Text #15

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.7970. Min Act: -0.0000

Data Index: 180663 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.6886. Min Act: -0.0000

Data Index: 1265310 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.6794. Min Act: -0.0000

Data Index: 1125252 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.6641. Min Act: -0.0000

Data Index: 672966 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 2.6704. Min Range: -2.6704

Max Act: 1.5583. Min Act: -0.0000

Data Index: 305857 (C4 (Web Text))

Max Activating Token Index: 350