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

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

Neuron 720 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: 0.0636. Min Range: -0.0636

Max Act: 0.0636. Min Act: -0.0003

Data Index: 490338 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1131190 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0589. Min Act: -0.0003

Data Index: 1013948 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0599. Min Act: -0.0003

Data Index: 1296499 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0583. Min Act: -0.0003

Data Index: 797197 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0581. Min Act: -0.0003

Data Index: 514701 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0576. Min Act: -0.0003

Data Index: 854583 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0569. Min Act: -0.0003

Data Index: 1107499 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0566. Min Act: -0.0003

Data Index: 255428 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0557. Min Act: -0.0003

Data Index: 1205961 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0547. Min Act: -0.0003

Data Index: 199617 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0557. Min Act: -0.0003

Data Index: 1171943 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0558. Min Act: -0.0003

Data Index: 799983 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0570. Min Act: -0.0003

Data Index: 611166 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0533. Min Act: -0.0003

Data Index: 935391 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0571. Min Act: -0.0003

Data Index: 219668 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0554. Min Act: -0.0003

Data Index: 823493 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0549. Min Act: -0.0003

Data Index: 517662 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0543. Min Act: -0.0003

Data Index: 466447 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0547. Min Act: -0.0003

Data Index: 590255 (C4 (Web Text))

Max Activating Token Index: 470