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

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

Neuron 1886 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.5404. Min Act: -0.0002

Data Index: 41166 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4581. Min Act: -0.0001

Data Index: 1309039 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.5098. Min Act: -0.0002

Data Index: 628992 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4579. Min Act: -0.0002

Data Index: 219010 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4948. Min Act: -0.0001

Data Index: 564374 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.5414. Min Act: -0.0002

Data Index: 778804 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.5012. Min Act: -0.0001

Data Index: 925999 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4686. Min Act: -0.0001

Data Index: 1325437 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4122. Min Act: -0.0002

Data Index: 340315 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4259. Min Act: -0.0001

Data Index: 472827 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4084. Min Act: -0.0002

Data Index: 403676 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.3867. Min Act: -0.0001

Data Index: 1138582 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4427. Min Act: -0.0001

Data Index: 302957 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.3807. Min Act: -0.0001

Data Index: 59576 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4053. Min Act: -0.0002

Data Index: 906099 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.3952. Min Act: -0.0002

Data Index: 564373 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4249. Min Act: -0.0002

Data Index: 767853 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4342. Min Act: -0.0002

Data Index: 570287 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4351. Min Act: -0.0002

Data Index: 1260978 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.5414. Min Range: -0.5414

Max Act: 0.4208. Min Act: -0.0002

Data Index: 862791 (C4 (Web Text))

Max Activating Token Index: 327