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

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

Neuron 1058 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: 0.0748. Min Range: -0.0748

Max Act: 0.0746. Min Act: -0.0003

Data Index: 329007 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0712. Min Act: -0.0003

Data Index: 827443 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0748. Min Act: -0.0003

Data Index: 1119146 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0705. Min Act: -0.0004

Data Index: 315553 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0665. Min Act: -0.0003

Data Index: 164751 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0670. Min Act: -0.0003

Data Index: 208173 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0646. Min Act: -0.0003

Data Index: 654060 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1060122 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0642. Min Act: -0.0003

Data Index: 543351 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0620. Min Act: -0.0003

Data Index: 631751 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0638. Min Act: -0.0003

Data Index: 883539 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0623. Min Act: -0.0003

Data Index: 903627 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0639. Min Act: -0.0003

Data Index: 208626 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0630. Min Act: -0.0004

Data Index: 579433 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0618. Min Act: -0.0004

Data Index: 19322 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0640. Min Act: -0.0003

Data Index: 438624 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0599. Min Act: -0.0003

Data Index: 445063 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0572. Min Act: -0.0004

Data Index: 1017749 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0576. Min Act: -0.0003

Data Index: 1311091 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0605. Min Act: -0.0003

Data Index: 707493 (C4 (Web Text))

Max Activating Token Index: 873