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

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

Neuron 2020 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.5393. Min Act: -0.0001

Data Index: 1167883 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.5067. Min Act: -0.0001

Data Index: 193089 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.4980. Min Act: -0.0001

Data Index: 1261667 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.4469. Min Act: -0.0001

Data Index: 423611 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.4199. Min Act: -0.0001

Data Index: 466364 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3907. Min Act: -0.0002

Data Index: 368906 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.4575. Min Act: -0.0001

Data Index: 252241 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3417. Min Act: -0.0001

Data Index: 1121313 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3408. Min Act: -0.0001

Data Index: 549370 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.4471. Min Act: -0.0001

Data Index: 329087 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3605. Min Act: -0.0001

Data Index: 1148445 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.4143. Min Act: -0.0001

Data Index: 923830 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.4116. Min Act: -0.0001

Data Index: 638543 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.2995. Min Act: -0.0001

Data Index: 1196013 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3848. Min Act: -0.0001

Data Index: 727131 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3996. Min Act: -0.0001

Data Index: 108929 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3849. Min Act: -0.0001

Data Index: 799489 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.4217. Min Act: -0.0001

Data Index: 734654 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3964. Min Act: -0.0001

Data Index: 722870 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.5393. Min Range: -0.5393

Max Act: 0.3773. Min Act: -0.0001

Data Index: 31746 (C4 (Web Text))

Max Activating Token Index: 872