Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2811 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2828. Min Act: -0.0000

Data Index: 1178572 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2225. Min Act: -0.0000

Data Index: 732911 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1668. Min Act: -0.0001

Data Index: 755639 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1716. Min Act: -0.0000

Data Index: 989452 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1641. Min Act: -0.0001

Data Index: 924323 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1684. Min Act: -0.0000

Data Index: 862382 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1667. Min Act: -0.0001

Data Index: 416742 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1199274 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1628. Min Act: -0.0001

Data Index: 759160 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1622. Min Act: 0.0000

Data Index: 117250 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1548. Min Act: -0.0001

Data Index: 468654 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1604. Min Act: -0.0001

Data Index: 1032102 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1584. Min Act: -0.0001

Data Index: 560697 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1638. Min Act: -0.0001

Data Index: 1270817 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1586. Min Act: -0.0001

Data Index: 1021862 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1614. Min Act: -0.0001

Data Index: 351645 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1553. Min Act: -0.0000

Data Index: 371334 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1486. Min Act: -0.0001

Data Index: 582764 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1532. Min Act: -0.0000

Data Index: 798628 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1567. Min Act: -0.0001

Data Index: 709615 (C4 (Web Text))

Max Activating Token Index: 762