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

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

Neuron 4 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: 0.0718. Min Range: -0.0718

Max Act: 0.0718. Min Act: -0.0000

Data Index: 962698 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0661. Min Act: -0.0000

Data Index: 456717 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0640. Min Act: -0.0000

Data Index: 1255798 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0611. Min Act: -0.0000

Data Index: 275504 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0624. Min Act: -0.0000

Data Index: 484529 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0596. Min Act: -0.0000

Data Index: 1188686 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0615. Min Act: -0.0000

Data Index: 1057299 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0595. Min Act: -0.0000

Data Index: 244243 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0593. Min Act: -0.0000

Data Index: 1157920 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0634. Min Act: -0.0000

Data Index: 148692 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1140515 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0599. Min Act: -0.0000

Data Index: 986056 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0610. Min Act: -0.0000

Data Index: 299629 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0548. Min Act: -0.0000

Data Index: 1048004 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0546. Min Act: -0.0000

Data Index: 884767 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0603. Min Act: -0.0000

Data Index: 14305 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0519. Min Act: -0.0000

Data Index: 1004882 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0561. Min Act: -0.0000

Data Index: 111077 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0542. Min Act: -0.0000

Data Index: 425630 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0537. Min Act: -0.0000

Data Index: 106344 (C4 (Web Text))

Max Activating Token Index: 214