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

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

Neuron 3060 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: 2.8184. Min Range: -2.8184

Max Act: 2.8184. Min Act: -0.0000

Data Index: 1557560 (Python Code)

Max Activating Token Index: 69

Text #1

Max Range: 2.8184. Min Range: -2.8184

Max Act: 2.7960. Min Act: -0.0000

Data Index: 246298 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 2.8184. Min Range: -2.8184

Max Act: 2.4980. Min Act: -0.0000

Data Index: 336637 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 2.8184. Min Range: -2.8184

Max Act: 2.8104. Min Act: -0.0000

Data Index: 394609 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 2.8184. Min Range: -2.8184

Max Act: 2.6468. Min Act: -0.0000

Data Index: 148627 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 2.8184. Min Range: -2.8184

Max Act: 2.5984. Min Act: -0.0000

Data Index: 292524 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 2.8184. Min Range: -2.8184

Max Act: 2.6172. Min Act: -0.0000

Data Index: 989408 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 2.8184. Min Range: -2.8184

Max Act: 2.4424. Min Act: -0.0000

Data Index: 1217847 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 2.8184. Min Range: -2.8184

Max Act: 2.4229. Min Act: -0.0000

Data Index: 1272574 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 2.8184. Min Range: -2.8184

Max Act: 2.4879. Min Act: -0.0000

Data Index: 540240 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 2.8184. Min Range: -2.8184

Max Act: 2.3509. Min Act: -0.0000

Data Index: 1123938 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 2.8184. Min Range: -2.8184

Max Act: 2.3166. Min Act: -0.0000

Data Index: 1016452 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 2.8184. Min Range: -2.8184

Max Act: 2.1639. Min Act: -0.0000

Data Index: 285029 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 2.8184. Min Range: -2.8184

Max Act: 2.6815. Min Act: -0.0000

Data Index: 575949 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 2.8184. Min Range: -2.8184

Max Act: 2.3961. Min Act: -0.0000

Data Index: 1041478 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 2.8184. Min Range: -2.8184

Max Act: 2.5199. Min Act: -0.0000

Data Index: 325305 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 2.8184. Min Range: -2.8184

Max Act: 2.3539. Min Act: -0.0000

Data Index: 523155 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 2.8184. Min Range: -2.8184

Max Act: 2.3603. Min Act: -0.0000

Data Index: 639998 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 2.8184. Min Range: -2.8184

Max Act: 2.4729. Min Act: -0.0000

Data Index: 1172849 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 2.8184. Min Range: -2.8184

Max Act: 2.3418. Min Act: -0.0000

Data Index: 478828 (C4 (Web Text))

Max Activating Token Index: 253