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

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

Neuron 4170 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0758. Min Act: -0.0002

Data Index: 486517 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0777. Min Act: -0.0002

Data Index: 808816 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1086753 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0771. Min Act: -0.0002

Data Index: 416430 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0754. Min Act: -0.0002

Data Index: 79033 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1315302 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0725. Min Act: -0.0002

Data Index: 851691 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1224212 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1135509 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0682. Min Act: -0.0002

Data Index: 123863 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0702. Min Act: -0.0002

Data Index: 378503 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0694. Min Act: -0.0002

Data Index: 307021 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0665. Min Act: -0.0002

Data Index: 676996 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0633. Min Act: -0.0002

Data Index: 10831 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0639. Min Act: -0.0002

Data Index: 812829 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0651. Min Act: -0.0002

Data Index: 533366 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0652. Min Act: -0.0002

Data Index: 482236 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0623. Min Act: -0.0002

Data Index: 194955 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1202477 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1297222 (C4 (Web Text))

Max Activating Token Index: 66