Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 702 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.4210. Min Act: -0.0005

Data Index: 259840 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.3886. Min Act: -0.0005

Data Index: 1144099 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.3237. Min Act: -0.0005

Data Index: 181172 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.3098. Min Act: -0.0005

Data Index: 796958 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.3302. Min Act: -0.0005

Data Index: 942785 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.3522. Min Act: -0.0005

Data Index: 514980 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.3218. Min Act: -0.0005

Data Index: 452329 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.3132. Min Act: -0.0005

Data Index: 897868 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.3188. Min Act: -0.0005

Data Index: 760289 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.2659. Min Act: -0.0005

Data Index: 49512 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.3132. Min Act: -0.0005

Data Index: 392455 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.2522. Min Act: -0.0005

Data Index: 176295 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.2689. Min Act: -0.0005

Data Index: 449841 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.2757. Min Act: -0.0005

Data Index: 1190281 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.2685. Min Act: -0.0004

Data Index: 71418 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.2350. Min Act: -0.0005

Data Index: 588651 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.2540. Min Act: -0.0005

Data Index: 19547 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.2433. Min Act: -0.0005

Data Index: 1214114 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.2711. Min Act: -0.0005

Data Index: 736192 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.4210. Min Range: -0.4210

Max Act: 0.2870. Min Act: -0.0005

Data Index: 1273632 (C4 (Web Text))

Max Activating Token Index: 869