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

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

Neuron 1103 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9411. Min Range: -1.9411

Max Act: 1.9411. Min Act: -0.0000

Data Index: 600348 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 1.9411. Min Range: -1.9411

Max Act: 1.6693. Min Act: -0.0000

Data Index: 1504996 (Python Code)

Max Activating Token Index: 53

Text #2

Max Range: 1.9411. Min Range: -1.9411

Max Act: 1.3473. Min Act: -0.0000

Data Index: 664720 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 1.9411. Min Range: -1.9411

Max Act: 1.5009. Min Act: -0.0000

Data Index: 282820 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 1.9411. Min Range: -1.9411

Max Act: 1.3627. Min Act: -0.0000

Data Index: 1652606 (Python Code)

Max Activating Token Index: 726

Text #5

Max Range: 1.9411. Min Range: -1.9411

Max Act: 1.3558. Min Act: -0.0000

Data Index: 1539985 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 1.9411. Min Range: -1.9411

Max Act: 1.2504. Min Act: -0.0000

Data Index: 1649846 (Python Code)

Max Activating Token Index: 796

Text #7

Max Range: 1.9411. Min Range: -1.9411

Max Act: 1.2572. Min Act: -0.0000

Data Index: 1066664 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 1.9411. Min Range: -1.9411

Max Act: 1.2064. Min Act: -0.0000

Data Index: 1396685 (Python Code)

Max Activating Token Index: 233

Text #9

Max Range: 1.9411. Min Range: -1.9411

Max Act: 1.1628. Min Act: -0.0000

Data Index: 1272065 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 1.9411. Min Range: -1.9411

Max Act: 1.0949. Min Act: -0.0000

Data Index: 379082 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 1.9411. Min Range: -1.9411

Max Act: 1.0199. Min Act: -0.0000

Data Index: 1063235 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 1.9411. Min Range: -1.9411

Max Act: 1.0251. Min Act: -0.0000

Data Index: 135915 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 1.9411. Min Range: -1.9411

Max Act: 1.0193. Min Act: -0.0000

Data Index: 80607 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 1.9411. Min Range: -1.9411

Max Act: 0.9434. Min Act: -0.0000

Data Index: 227750 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 1.9411. Min Range: -1.9411

Max Act: 1.0653. Min Act: -0.0000

Data Index: 368317 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 1.9411. Min Range: -1.9411

Max Act: 1.0627. Min Act: -0.0000

Data Index: 218234 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 1.9411. Min Range: -1.9411

Max Act: 1.1222. Min Act: -0.0000

Data Index: 22269 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 1.9411. Min Range: -1.9411

Max Act: 1.0546. Min Act: -0.0000

Data Index: 341302 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 1.9411. Min Range: -1.9411

Max Act: 1.0420. Min Act: -0.0000

Data Index: 1488482 (Python Code)

Max Activating Token Index: 271