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

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

Neuron 4607 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: 3.8527. Min Range: -3.8527

Max Act: 3.8527. Min Act: -0.0000

Data Index: 201404 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.3632. Min Act: -0.0000

Data Index: 591581 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.3632. Min Act: -0.0000

Data Index: 1098551 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.0739. Min Act: -0.0000

Data Index: 107922 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.0952. Min Act: -0.0000

Data Index: 939262 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.0532. Min Act: -0.0000

Data Index: 925493 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 3.8527. Min Range: -3.8527

Max Act: 2.9134. Min Act: -0.0000

Data Index: 977897 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 3.8527. Min Range: -3.8527

Max Act: 2.8362. Min Act: -0.0000

Data Index: 459407 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 3.8527. Min Range: -3.8527

Max Act: 2.7047. Min Act: -0.0000

Data Index: 296618 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 3.8527. Min Range: -3.8527

Max Act: 2.6655. Min Act: -0.0000

Data Index: 667606 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 3.8527. Min Range: -3.8527

Max Act: 2.6372. Min Act: -0.0000

Data Index: 468681 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 3.8527. Min Range: -3.8527

Max Act: 2.7784. Min Act: -0.0000

Data Index: 448188 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 3.8527. Min Range: -3.8527

Max Act: 2.6011. Min Act: -0.0000

Data Index: 645327 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 3.8527. Min Range: -3.8527

Max Act: 2.5969. Min Act: -0.0000

Data Index: 209186 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 3.8527. Min Range: -3.8527

Max Act: 2.5454. Min Act: -0.0000

Data Index: 1029126 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 3.8527. Min Range: -3.8527

Max Act: 2.5103. Min Act: -0.0000

Data Index: 228715 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 3.8527. Min Range: -3.8527

Max Act: 2.3767. Min Act: -0.0000

Data Index: 632463 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 3.8527. Min Range: -3.8527

Max Act: 2.4919. Min Act: -0.0000

Data Index: 866702 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 3.8527. Min Range: -3.8527

Max Act: 2.4544. Min Act: -0.0000

Data Index: 601348 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 3.8527. Min Range: -3.8527

Max Act: 2.4116. Min Act: -0.0000

Data Index: 222518 (C4 (Web Text))

Max Activating Token Index: 945