Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3578 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2941. Min Act: -0.0000

Data Index: 364945 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2984. Min Act: -0.0000

Data Index: 584506 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.2732. Min Act: -0.0000

Data Index: 409319 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.0779. Min Act: -0.0000

Data Index: 993895 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 3.2984. Min Range: -3.2984

Max Act: 2.9431. Min Act: -0.0000

Data Index: 300659 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.0487. Min Act: -0.0000

Data Index: 727443 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 3.2984. Min Range: -3.2984

Max Act: 2.8709. Min Act: -0.0000

Data Index: 766256 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 3.2984. Min Range: -3.2984

Max Act: 2.8268. Min Act: -0.0000

Data Index: 177184 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 3.2984. Min Range: -3.2984

Max Act: 2.9246. Min Act: -0.0000

Data Index: 559874 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 3.2984. Min Range: -3.2984

Max Act: 2.9284. Min Act: -0.0000

Data Index: 998289 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 3.2984. Min Range: -3.2984

Max Act: 3.0204. Min Act: -0.0000

Data Index: 487292 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 3.2984. Min Range: -3.2984

Max Act: 2.8470. Min Act: -0.0000

Data Index: 1046522 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 3.2984. Min Range: -3.2984

Max Act: 2.6931. Min Act: -0.0000

Data Index: 1338391 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 3.2984. Min Range: -3.2984

Max Act: 2.6589. Min Act: -0.0000

Data Index: 644556 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 3.2984. Min Range: -3.2984

Max Act: 2.7817. Min Act: -0.0000

Data Index: 831469 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 3.2984. Min Range: -3.2984

Max Act: 2.8976. Min Act: -0.0000

Data Index: 801897 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 3.2984. Min Range: -3.2984

Max Act: 2.7120. Min Act: -0.0000

Data Index: 695801 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 3.2984. Min Range: -3.2984

Max Act: 2.7968. Min Act: -0.0000

Data Index: 31626 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 3.2984. Min Range: -3.2984

Max Act: 2.6738. Min Act: -0.0000

Data Index: 80689 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 3.2984. Min Range: -3.2984

Max Act: 2.5250. Min Act: -0.0000

Data Index: 69455 (C4 (Web Text))

Max Activating Token Index: 120