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

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

Neuron 1445 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5491. Min Range: -2.5491

Max Act: 2.4357. Min Act: -0.0000

Data Index: 179590 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 2.5491. Min Range: -2.5491

Max Act: 2.5491. Min Act: -0.0000

Data Index: 833716 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 2.5491. Min Range: -2.5491

Max Act: 2.2704. Min Act: -0.0000

Data Index: 1301064 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 2.5491. Min Range: -2.5491

Max Act: 2.2574. Min Act: 0.0000

Data Index: 1040483 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 2.5491. Min Range: -2.5491

Max Act: 2.1264. Min Act: -0.0000

Data Index: 102020 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 2.5491. Min Range: -2.5491

Max Act: 1.9230. Min Act: -0.0000

Data Index: 201 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 2.5491. Min Range: -2.5491

Max Act: 2.0954. Min Act: -0.0000

Data Index: 74950 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 2.5491. Min Range: -2.5491

Max Act: 1.7661. Min Act: -0.0000

Data Index: 939150 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 2.5491. Min Range: -2.5491

Max Act: 1.9536. Min Act: 0.0000

Data Index: 300536 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 2.5491. Min Range: -2.5491

Max Act: 1.8258. Min Act: -0.0000

Data Index: 1081608 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 2.5491. Min Range: -2.5491

Max Act: 1.8514. Min Act: -0.0000

Data Index: 1385087 (Python Code)

Max Activating Token Index: 900

Text #11

Max Range: 2.5491. Min Range: -2.5491

Max Act: 1.8281. Min Act: -0.0000

Data Index: 754855 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 2.5491. Min Range: -2.5491

Max Act: 1.8998. Min Act: -0.0000

Data Index: 587696 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 2.5491. Min Range: -2.5491

Max Act: 1.8761. Min Act: -0.0000

Data Index: 690914 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 2.5491. Min Range: -2.5491

Max Act: 1.7475. Min Act: -0.0000

Data Index: 382537 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 2.5491. Min Range: -2.5491

Max Act: 1.5396. Min Act: -0.0000

Data Index: 741239 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 2.5491. Min Range: -2.5491

Max Act: 1.7184. Min Act: -0.0000

Data Index: 928318 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 2.5491. Min Range: -2.5491

Max Act: 1.6275. Min Act: -0.0000

Data Index: 1213449 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 2.5491. Min Range: -2.5491

Max Act: 1.6927. Min Act: -0.0000

Data Index: 198635 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 2.5491. Min Range: -2.5491

Max Act: 1.6808. Min Act: -0.0000

Data Index: 404307 (C4 (Web Text))

Max Activating Token Index: 372