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

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

Neuron 2393 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.4268. Min Act: -0.0000

Data Index: 156974 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3737. Min Act: -0.0000

Data Index: 1638173 (Python Code)

Max Activating Token Index: 352

Text #2

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3914. Min Act: -0.0000

Data Index: 574716 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1262047 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3786. Min Act: -0.0000

Data Index: 837895 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3683. Min Act: -0.0000

Data Index: 841546 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3609. Min Act: -0.0000

Data Index: 787954 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3371. Min Act: -0.0000

Data Index: 973219 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3398. Min Act: -0.0000

Data Index: 477820 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3217. Min Act: -0.0000

Data Index: 615925 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3430. Min Act: -0.0000

Data Index: 973223 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3349. Min Act: -0.0000

Data Index: 492710 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1294552 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1080911 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3110. Min Act: -0.0000

Data Index: 54794 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1149699 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3019. Min Act: -0.0000

Data Index: 55289 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3084. Min Act: -0.0000

Data Index: 1280031 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3160. Min Act: -0.0000

Data Index: 572230 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 0.4268. Min Range: -0.4268

Max Act: 0.3161. Min Act: -0.0000

Data Index: 929909 (C4 (Web Text))

Max Activating Token Index: 412