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

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

Neuron 3252 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2594. Min Act: -0.0000

Data Index: 828300 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2424. Min Act: -0.0000

Data Index: 740436 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2555. Min Act: -0.0000

Data Index: 1058503 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2407. Min Act: -0.0000

Data Index: 968415 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2519. Min Act: -0.0000

Data Index: 844489 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2265. Min Act: -0.0000

Data Index: 237420 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2334. Min Act: -0.0000

Data Index: 634048 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.1993. Min Act: -0.0000

Data Index: 374472 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2346. Min Act: -0.0000

Data Index: 355316 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2122. Min Act: -0.0000

Data Index: 253241 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2113. Min Act: -0.0000

Data Index: 402228 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2240. Min Act: -0.0000

Data Index: 354315 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2007. Min Act: -0.0000

Data Index: 620016 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1012462 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.1986. Min Act: -0.0000

Data Index: 654722 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2044. Min Act: -0.0000

Data Index: 587887 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2003. Min Act: -0.0000

Data Index: 281664 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2043. Min Act: -0.0000

Data Index: 283362 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2093. Min Act: -0.0000

Data Index: 369410 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.1940. Min Act: -0.0000

Data Index: 515004 (C4 (Web Text))

Max Activating Token Index: 158