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

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

Neuron 501 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.4244. Min Act: -0.0000

Data Index: 455482 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.2011. Min Act: -0.0001

Data Index: 660126 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.2674. Min Act: -0.0000

Data Index: 243473 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.2041. Min Act: -0.0000

Data Index: 1098539 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.3038. Min Act: -0.0000

Data Index: 300196 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.2151. Min Act: -0.0000

Data Index: 594529 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.2545. Min Act: -0.0001

Data Index: 645130 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.1813. Min Act: -0.0000

Data Index: 1610633 (Python Code)

Max Activating Token Index: 232

Text #8

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.1312. Min Act: -0.0000

Data Index: 387048 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.2356. Min Act: -0.0001

Data Index: 872323 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.1365. Min Act: -0.0001

Data Index: 666588 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.1277. Min Act: -0.0001

Data Index: 1198723 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.0807. Min Act: -0.0001

Data Index: 185207 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.1533. Min Act: -0.0000

Data Index: 479027 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.1187. Min Act: -0.0000

Data Index: 743332 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.0794. Min Act: -0.0000

Data Index: 1019736 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.0820. Min Act: -0.0000

Data Index: 873070 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.0991. Min Act: -0.0000

Data Index: 304053 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.0673. Min Act: -0.0001

Data Index: 1171106 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.0547. Min Act: -0.0001

Data Index: 335846 (C4 (Web Text))

Max Activating Token Index: 890