Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 320 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0910. Min Act: -0.0001

Data Index: 940668 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0732. Min Act: -0.0001

Data Index: 4188 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0753. Min Act: -0.0001

Data Index: 1321582 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0685. Min Act: -0.0001

Data Index: 945778 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0706. Min Act: -0.0001

Data Index: 1213672 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0663. Min Act: -0.0001

Data Index: 971841 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0682. Min Act: -0.0001

Data Index: 729583 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0617. Min Act: -0.0001

Data Index: 18957 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0611. Min Act: -0.0001

Data Index: 317694 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1264494 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0562. Min Act: -0.0001

Data Index: 326053 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0597. Min Act: -0.0001

Data Index: 78580 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0790. Min Act: -0.0001

Data Index: 140304 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0494. Min Act: -0.0001

Data Index: 389110 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0630. Min Act: -0.0001

Data Index: 593251 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0621. Min Act: -0.0001

Data Index: 816108 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0525. Min Act: -0.0001

Data Index: 112550 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0559. Min Act: -0.0001

Data Index: 471619 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0634. Min Act: -0.0001

Data Index: 408798 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0500. Min Act: -0.0001

Data Index: 365370 (C4 (Web Text))

Max Activating Token Index: 280