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

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

Neuron 4352 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.9949. Min Act: -0.0000

Data Index: 1254703 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.5831. Min Act: -0.0000

Data Index: 1025597 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.4981. Min Act: -0.0000

Data Index: 512647 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.4829. Min Act: -0.0000

Data Index: 108643 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.4289. Min Act: -0.0000

Data Index: 274909 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.4349. Min Act: -0.0000

Data Index: 964840 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.3828. Min Act: -0.0000

Data Index: 138914 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1179129 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.3815. Min Act: -0.0000

Data Index: 146902 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.4008. Min Act: -0.0000

Data Index: 1265488 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.4001. Min Act: -0.0000

Data Index: 1053877 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.3941. Min Act: -0.0000

Data Index: 280485 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.3979. Min Act: -0.0000

Data Index: 283223 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.3834. Min Act: -0.0000

Data Index: 1354737 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.4043. Min Act: -0.0000

Data Index: 1258749 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1288947 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.3605. Min Act: -0.0000

Data Index: 146430 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.3606. Min Act: -0.0000

Data Index: 1198245 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.3775. Min Act: -0.0000

Data Index: 1268614 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.9949. Min Range: -0.9949

Max Act: 0.3647. Min Act: -0.0000

Data Index: 62258 (C4 (Web Text))

Max Activating Token Index: 764