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

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

Neuron 1537 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: 0.0605. Min Range: -0.0605

Max Act: 0.0605. Min Act: -0.0003

Data Index: 1308794 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0584. Min Act: -0.0003

Data Index: 1142656 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0578. Min Act: -0.0004

Data Index: 127155 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0569. Min Act: -0.0003

Data Index: 907325 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0565. Min Act: -0.0004

Data Index: 542126 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0572. Min Act: -0.0003

Data Index: 772555 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1113241 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0577. Min Act: -0.0004

Data Index: 911023 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0557. Min Act: -0.0004

Data Index: 241602 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0544. Min Act: -0.0003

Data Index: 6040 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0531. Min Act: -0.0003

Data Index: 990661 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0560. Min Act: -0.0003

Data Index: 1151755 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0558. Min Act: -0.0003

Data Index: 1143767 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0574. Min Act: -0.0003

Data Index: 558986 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0553. Min Act: -0.0003

Data Index: 377047 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0562. Min Act: -0.0003

Data Index: 1032832 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0539. Min Act: -0.0003

Data Index: 549286 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0538. Min Act: -0.0003

Data Index: 1332926 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0536. Min Act: -0.0003

Data Index: 1218422 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0545. Min Act: -0.0003

Data Index: 1320904 (C4 (Web Text))

Max Activating Token Index: 328