Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3607 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.4984. Min Act: -0.0000

Data Index: 43853 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.4242. Min Act: -0.0000

Data Index: 518114 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.4828. Min Act: 0.0000

Data Index: 1004740 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.3708. Min Act: -0.0000

Data Index: 697818 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.2059. Min Act: -0.0000

Data Index: 905731 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.1584. Min Act: -0.0000

Data Index: 609721 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.1894. Min Act: -0.0000

Data Index: 68375 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.0882. Min Act: -0.0000

Data Index: 693469 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.1443. Min Act: -0.0000

Data Index: 190764 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.1334. Min Act: 0.0000

Data Index: 622420 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.1186. Min Act: -0.0000

Data Index: 355604 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.1119. Min Act: -0.0000

Data Index: 225689 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.1561. Min Act: 0.0002

Data Index: 433007 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.0089. Min Act: 0.0001

Data Index: 870938 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.0294. Min Act: -0.0000

Data Index: 1132883 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.0530. Min Act: -0.0000

Data Index: 1066331 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 1.4984. Min Range: -1.4984

Max Act: 0.9877. Min Act: -0.0000

Data Index: 717974 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.0683. Min Act: -0.0000

Data Index: 658967 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.0034. Min Act: -0.0000

Data Index: 253252 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.0334. Min Act: -0.0000

Data Index: 401361 (C4 (Web Text))

Max Activating Token Index: 841