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

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

Neuron 3502 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0979. Min Range: -2.0979

Max Act: 2.0979. Min Act: -0.0000

Data Index: 1209732 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 2.0979. Min Range: -2.0979

Max Act: 2.0503. Min Act: -0.0000

Data Index: 529595 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 2.0979. Min Range: -2.0979

Max Act: 2.0300. Min Act: -0.0000

Data Index: 753003 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.8562. Min Act: -0.0000

Data Index: 725301 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.8720. Min Act: -0.0000

Data Index: 1073886 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.8329. Min Act: -0.0000

Data Index: 159396 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.8134. Min Act: -0.0000

Data Index: 1294517 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.8525. Min Act: -0.0000

Data Index: 331359 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.8442. Min Act: -0.0000

Data Index: 1134000 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.6625. Min Act: -0.0000

Data Index: 890527 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.6494. Min Act: -0.0000

Data Index: 766386 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.6034. Min Act: -0.0000

Data Index: 1293316 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.6977. Min Act: -0.0000

Data Index: 410285 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.6601. Min Act: -0.0000

Data Index: 978703 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.5555. Min Act: -0.0000

Data Index: 1103161 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.5972. Min Act: -0.0000

Data Index: 470911 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.2975. Min Act: -0.0000

Data Index: 255431 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.3873. Min Act: -0.0000

Data Index: 1242322 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.4111. Min Act: -0.0000

Data Index: 129920 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.4515. Min Act: -0.0000

Data Index: 1134851 (C4 (Web Text))

Max Activating Token Index: 766