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

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

Neuron 2410 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0924. Min Range: -1.0924

Max Act: 1.0252. Min Act: -0.0000

Data Index: 414256 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 1.0924. Min Range: -1.0924

Max Act: 1.0413. Min Act: -0.0000

Data Index: 260948 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 1.0924. Min Range: -1.0924

Max Act: 1.0763. Min Act: -0.0000

Data Index: 1040678 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8862. Min Act: -0.0000

Data Index: 130821 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9647. Min Act: -0.0000

Data Index: 980321 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 1.0924. Min Range: -1.0924

Max Act: 1.0924. Min Act: -0.0000

Data Index: 516813 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8722. Min Act: -0.0000

Data Index: 475908 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9290. Min Act: -0.0000

Data Index: 565760 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9340. Min Act: -0.0000

Data Index: 68746 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9162. Min Act: -0.0000

Data Index: 1071806 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9415. Min Act: -0.0000

Data Index: 1136071 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8778. Min Act: -0.0000

Data Index: 86132 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1334904 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9441. Min Act: -0.0000

Data Index: 127747 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.7891. Min Act: -0.0000

Data Index: 390423 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8627. Min Act: -0.0000

Data Index: 1121234 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9158. Min Act: -0.0000

Data Index: 250171 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8562. Min Act: -0.0000

Data Index: 909096 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8600. Min Act: -0.0000

Data Index: 897438 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8318. Min Act: -0.0000

Data Index: 1025484 (C4 (Web Text))

Max Activating Token Index: 871