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

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

Neuron 4353 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: 0.8099. Min Range: -0.8099

Max Act: 0.7756. Min Act: -0.0000

Data Index: 492726 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.7995. Min Act: -0.0000

Data Index: 573258 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1293298 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.7521. Min Act: -0.0000

Data Index: 765879 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.7415. Min Act: -0.0000

Data Index: 110849 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.7330. Min Act: -0.0000

Data Index: 526658 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6856. Min Act: -0.0000

Data Index: 232549 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6986. Min Act: -0.0000

Data Index: 490134 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1103339 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1249751 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6915. Min Act: -0.0000

Data Index: 600007 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6634. Min Act: -0.0000

Data Index: 156460 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6320. Min Act: -0.0000

Data Index: 1158453 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6341. Min Act: -0.0000

Data Index: 798267 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6317. Min Act: -0.0000

Data Index: 423719 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6216. Min Act: -0.0000

Data Index: 1299988 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6150. Min Act: -0.0000

Data Index: 486389 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5964. Min Act: -0.0000

Data Index: 612034 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6305. Min Act: -0.0000

Data Index: 166028 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6364. Min Act: -0.0000

Data Index: 678699 (C4 (Web Text))

Max Activating Token Index: 435