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

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

Neuron 2524 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: 0.7856. Min Range: -0.7856

Max Act: 0.7856. Min Act: -0.0000

Data Index: 294097 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1315319 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.7773. Min Act: -0.0000

Data Index: 197616 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.7659. Min Act: -0.0000

Data Index: 385653 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6382. Min Act: -0.0000

Data Index: 936343 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6520. Min Act: -0.0000

Data Index: 974033 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.7097. Min Act: -0.0000

Data Index: 172872 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6520. Min Act: -0.0000

Data Index: 1279008 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6274. Min Act: -0.0000

Data Index: 729355 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6534. Min Act: -0.0000

Data Index: 672369 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6516. Min Act: -0.0000

Data Index: 1056071 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6333. Min Act: -0.0000

Data Index: 217010 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6516. Min Act: -0.0000

Data Index: 1134671 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6316. Min Act: -0.0000

Data Index: 2385 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6392. Min Act: -0.0000

Data Index: 839309 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.7293. Min Act: -0.0000

Data Index: 851883 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6023. Min Act: -0.0000

Data Index: 956198 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6337. Min Act: -0.0000

Data Index: 259527 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6118. Min Act: -0.0000

Data Index: 822611 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1330305 (C4 (Web Text))

Max Activating Token Index: 156