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

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

Neuron 3560 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0944. Min Act: -0.0000

Data Index: 9621 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0898. Min Act: -0.0000

Data Index: 411835 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1227598 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0757. Min Act: -0.0001

Data Index: 1135509 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0796. Min Act: -0.0000

Data Index: 201498 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0719. Min Act: -0.0000

Data Index: 322956 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0714. Min Act: -0.0000

Data Index: 771527 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0697. Min Act: -0.0001

Data Index: 342656 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0738. Min Act: -0.0000

Data Index: 754330 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0701. Min Act: -0.0000

Data Index: 608985 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0681. Min Act: -0.0000

Data Index: 445380 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0671. Min Act: -0.0000

Data Index: 1005961 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0721. Min Act: -0.0000

Data Index: 467594 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0642. Min Act: -0.0000

Data Index: 835778 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0640. Min Act: -0.0000

Data Index: 938165 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0659. Min Act: -0.0001

Data Index: 438249 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0595. Min Act: -0.0000

Data Index: 221996 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0634. Min Act: -0.0000

Data Index: 395578 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0626. Min Act: -0.0000

Data Index: 994702 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0627. Min Act: -0.0000

Data Index: 647313 (C4 (Web Text))

Max Activating Token Index: 316