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

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

Neuron 513 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: 0.0677. Min Range: -0.0677

Max Act: 0.0661. Min Act: -0.0001

Data Index: 87280 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0677. Min Act: -0.0001

Data Index: 412634 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0635. Min Act: -0.0001

Data Index: 820899 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0641. Min Act: -0.0001

Data Index: 374869 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0629. Min Act: -0.0001

Data Index: 161678 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0568. Min Act: -0.0001

Data Index: 120817 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0569. Min Act: -0.0001

Data Index: 1076283 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0630. Min Act: -0.0001

Data Index: 475662 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0565. Min Act: -0.0001

Data Index: 594553 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0562. Min Act: -0.0001

Data Index: 1312238 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0551. Min Act: -0.0001

Data Index: 632699 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0570. Min Act: -0.0001

Data Index: 578903 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0568. Min Act: -0.0001

Data Index: 235862 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0567. Min Act: -0.0001

Data Index: 50076 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0585. Min Act: -0.0001

Data Index: 831241 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0551. Min Act: -0.0001

Data Index: 107325 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0568. Min Act: -0.0001

Data Index: 1028686 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0566. Min Act: -0.0001

Data Index: 173944 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0539. Min Act: -0.0001

Data Index: 1291447 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0537. Min Act: -0.0001

Data Index: 870051 (C4 (Web Text))

Max Activating Token Index: 35