Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 105 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0880. Min Act: -0.0000

Data Index: 1185614 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1640006 (Python Code)

Max Activating Token Index: 149

Text #2

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0754. Min Act: -0.0000

Data Index: 904561 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0749. Min Act: 0.0000

Data Index: 1545324 (Python Code)

Max Activating Token Index: 141

Text #4

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0736. Min Act: 0.0000

Data Index: 193669 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0671. Min Act: 0.0000

Data Index: 885468 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0699. Min Act: 0.0000

Data Index: 34677 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0615. Min Act: -0.0000

Data Index: 1004626 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0617. Min Act: 0.0000

Data Index: 1103099 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0640. Min Act: 0.0000

Data Index: 484712 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1617063 (Python Code)

Max Activating Token Index: 117

Text #11

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0588. Min Act: 0.0000

Data Index: 1358077 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0470. Min Act: -0.0000

Data Index: 380722 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0543. Min Act: -0.0000

Data Index: 1049809 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0507. Min Act: -0.0000

Data Index: 1484888 (Python Code)

Max Activating Token Index: 206

Text #15

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0532. Min Act: 0.0000

Data Index: 512803 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0523. Min Act: -0.0000

Data Index: 1269649 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0549. Min Act: -0.0000

Data Index: 1046743 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0487. Min Act: -0.0000

Data Index: 160146 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0555. Min Act: -0.0000

Data Index: 665849 (C4 (Web Text))

Max Activating Token Index: 96