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

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

Neuron 2893 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6889. Min Range: -1.6889

Max Act: 1.6889. Min Act: -0.0000

Data Index: 1351255 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 1.6889. Min Range: -1.6889

Max Act: 1.3978. Min Act: -0.0000

Data Index: 148935 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 1.6889. Min Range: -1.6889

Max Act: 1.2196. Min Act: -0.0000

Data Index: 1246004 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 1.6889. Min Range: -1.6889

Max Act: 1.2664. Min Act: -0.0000

Data Index: 627397 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 1.6889. Min Range: -1.6889

Max Act: 1.0093. Min Act: -0.0000

Data Index: 692605 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 1.6889. Min Range: -1.6889

Max Act: 1.0110. Min Act: -0.0000

Data Index: 850456 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 1.6889. Min Range: -1.6889

Max Act: 1.0365. Min Act: -0.0000

Data Index: 659096 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 1.6889. Min Range: -1.6889

Max Act: 1.0200. Min Act: -0.0000

Data Index: 578230 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 1.6889. Min Range: -1.6889

Max Act: 1.0082. Min Act: -0.0000

Data Index: 1304135 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 1.6889. Min Range: -1.6889

Max Act: 0.9078. Min Act: -0.0000

Data Index: 440965 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 1.6889. Min Range: -1.6889

Max Act: 0.9467. Min Act: -0.0000

Data Index: 287281 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 1.6889. Min Range: -1.6889

Max Act: 0.9406. Min Act: -0.0000

Data Index: 764182 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 1.6889. Min Range: -1.6889

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1064282 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 1.6889. Min Range: -1.6889

Max Act: 0.9321. Min Act: -0.0000

Data Index: 133223 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 1.6889. Min Range: -1.6889

Max Act: 0.9942. Min Act: -0.0000

Data Index: 472519 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 1.6889. Min Range: -1.6889

Max Act: 0.9391. Min Act: -0.0000

Data Index: 600843 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 1.6889. Min Range: -1.6889

Max Act: 0.9787. Min Act: -0.0000

Data Index: 257752 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 1.6889. Min Range: -1.6889

Max Act: 0.8381. Min Act: -0.0000

Data Index: 1200827 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 1.6889. Min Range: -1.6889

Max Act: 0.8815. Min Act: -0.0000

Data Index: 278292 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 1.6889. Min Range: -1.6889

Max Act: 0.8360. Min Act: -0.0000

Data Index: 237878 (C4 (Web Text))

Max Activating Token Index: 526