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

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

Neuron 4727 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7977. Min Range: -2.7977

Max Act: 2.7977. Min Act: -0.0000

Data Index: 717630 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 2.7977. Min Range: -2.7977

Max Act: 2.3400. Min Act: -0.0000

Data Index: 704858 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 2.7977. Min Range: -2.7977

Max Act: 2.2609. Min Act: -0.0000

Data Index: 575838 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 2.7977. Min Range: -2.7977

Max Act: 2.2162. Min Act: -0.0000

Data Index: 788545 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 2.7977. Min Range: -2.7977

Max Act: 1.9649. Min Act: -0.0000

Data Index: 732616 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 2.7977. Min Range: -2.7977

Max Act: 2.0749. Min Act: -0.0000

Data Index: 663828 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 2.7977. Min Range: -2.7977

Max Act: 2.1563. Min Act: -0.0000

Data Index: 440272 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 2.7977. Min Range: -2.7977

Max Act: 2.0169. Min Act: -0.0000

Data Index: 981648 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 2.7977. Min Range: -2.7977

Max Act: 1.9538. Min Act: -0.0000

Data Index: 593264 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 2.7977. Min Range: -2.7977

Max Act: 1.9538. Min Act: -0.0000

Data Index: 458641 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 2.7977. Min Range: -2.7977

Max Act: 1.8098. Min Act: -0.0000

Data Index: 495540 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 2.7977. Min Range: -2.7977

Max Act: 1.6969. Min Act: -0.0000

Data Index: 542349 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 2.7977. Min Range: -2.7977

Max Act: 1.6914. Min Act: -0.0000

Data Index: 1103049 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 2.7977. Min Range: -2.7977

Max Act: 1.7686. Min Act: -0.0000

Data Index: 516021 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 2.7977. Min Range: -2.7977

Max Act: 1.6696. Min Act: -0.0000

Data Index: 352057 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 2.7977. Min Range: -2.7977

Max Act: 1.6418. Min Act: -0.0000

Data Index: 281268 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 2.7977. Min Range: -2.7977

Max Act: 1.6237. Min Act: -0.0000

Data Index: 1344213 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 2.7977. Min Range: -2.7977

Max Act: 1.6945. Min Act: -0.0000

Data Index: 576838 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 2.7977. Min Range: -2.7977

Max Act: 1.6943. Min Act: -0.0000

Data Index: 1052723 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 2.7977. Min Range: -2.7977

Max Act: 1.6678. Min Act: -0.0000

Data Index: 161103 (C4 (Web Text))

Max Activating Token Index: 127