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

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

Neuron 4539 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0960. Min Range: -4.0960

Max Act: 4.0960. Min Act: -0.0000

Data Index: 1197987 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.5334. Min Act: -0.0000

Data Index: 669951 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.2937. Min Act: -0.0000

Data Index: 852630 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.3767. Min Act: -0.0000

Data Index: 88544 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.2112. Min Act: -0.0000

Data Index: 459502 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.1486. Min Act: -0.0000

Data Index: 248264 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.1254. Min Act: -0.0000

Data Index: 543243 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.2252. Min Act: -0.0000

Data Index: 113950 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 4.0960. Min Range: -4.0960

Max Act: 2.9218. Min Act: -0.0000

Data Index: 72474 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 4.0960. Min Range: -4.0960

Max Act: 3.0004. Min Act: -0.0000

Data Index: 891641 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 4.0960. Min Range: -4.0960

Max Act: 2.9580. Min Act: -0.0000

Data Index: 782064 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 4.0960. Min Range: -4.0960

Max Act: 2.9406. Min Act: -0.0000

Data Index: 1206213 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 4.0960. Min Range: -4.0960

Max Act: 2.7601. Min Act: -0.0000

Data Index: 14955 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 4.0960. Min Range: -4.0960

Max Act: 2.9642. Min Act: 0.0000

Data Index: 492039 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 4.0960. Min Range: -4.0960

Max Act: 2.9788. Min Act: -0.0000

Data Index: 446926 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 4.0960. Min Range: -4.0960

Max Act: 2.8097. Min Act: -0.0000

Data Index: 1125074 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 4.0960. Min Range: -4.0960

Max Act: 2.6222. Min Act: -0.0000

Data Index: 1150415 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 4.0960. Min Range: -4.0960

Max Act: 2.6255. Min Act: -0.0000

Data Index: 981015 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 4.0960. Min Range: -4.0960

Max Act: 2.5661. Min Act: -0.0000

Data Index: 119139 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 4.0960. Min Range: -4.0960

Max Act: 2.6227. Min Act: -0.0000

Data Index: 440403 (C4 (Web Text))

Max Activating Token Index: 350