Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1725 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0003

Data Index: 405937 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0784. Min Act: -0.0003

Data Index: 1223413 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0750. Min Act: -0.0003

Data Index: 1212226 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0698. Min Act: -0.0002

Data Index: 411363 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0688. Min Act: -0.0003

Data Index: 111044 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0686. Min Act: -0.0003

Data Index: 757606 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0657. Min Act: -0.0003

Data Index: 996270 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0642. Min Act: -0.0003

Data Index: 1203607 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0654. Min Act: -0.0003

Data Index: 194119 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0649. Min Act: -0.0003

Data Index: 546311 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0626. Min Act: -0.0002

Data Index: 251641 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0646. Min Act: -0.0003

Data Index: 210218 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0627. Min Act: -0.0002

Data Index: 675636 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0612. Min Act: -0.0003

Data Index: 936290 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0620. Min Act: -0.0003

Data Index: 458088 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0618. Min Act: -0.0003

Data Index: 899798 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0632. Min Act: -0.0003

Data Index: 910407 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0613. Min Act: -0.0003

Data Index: 1143501 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0631. Min Act: -0.0003

Data Index: 1115748 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0608. Min Act: -0.0002

Data Index: 188280 (C4 (Web Text))

Max Activating Token Index: 53