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

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

Neuron 1503 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: 0.0734. Min Range: -0.0734

Max Act: 0.0734. Min Act: -0.0002

Data Index: 979864 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0707. Min Act: -0.0003

Data Index: 576209 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0697. Min Act: -0.0004

Data Index: 232141 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0631. Min Act: -0.0002

Data Index: 999468 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0609. Min Act: -0.0003

Data Index: 211816 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0598. Min Act: -0.0003

Data Index: 1324060 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0602. Min Act: -0.0003

Data Index: 24614 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0582. Min Act: -0.0003

Data Index: 115371 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0607. Min Act: -0.0003

Data Index: 656138 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0585. Min Act: -0.0004

Data Index: 664001 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0638. Min Act: -0.0003

Data Index: 128967 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0608. Min Act: -0.0003

Data Index: 941886 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1018311 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0578. Min Act: -0.0003

Data Index: 99913 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0582. Min Act: -0.0004

Data Index: 787471 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0573. Min Act: -0.0003

Data Index: 1103047 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0564. Min Act: -0.0002

Data Index: 198654 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0562. Min Act: -0.0003

Data Index: 1296621 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0567. Min Act: -0.0003

Data Index: 1329181 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0565. Min Act: -0.0003

Data Index: 290751 (C4 (Web Text))

Max Activating Token Index: 144