Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1896 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.3098. Min Act: -0.0004

Data Index: 221649 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.3035. Min Act: -0.0003

Data Index: 497950 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2891. Min Act: -0.0004

Data Index: 877182 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2708. Min Act: -0.0003

Data Index: 613771 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2705. Min Act: -0.0003

Data Index: 290630 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2822. Min Act: -0.0003

Data Index: 345938 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2792. Min Act: -0.0003

Data Index: 107785 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2689. Min Act: -0.0003

Data Index: 847406 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2777. Min Act: -0.0003

Data Index: 1090957 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2874. Min Act: -0.0003

Data Index: 150319 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2751. Min Act: -0.0003

Data Index: 573408 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2731. Min Act: -0.0003

Data Index: 1067955 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2733. Min Act: -0.0003

Data Index: 710000 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2608. Min Act: -0.0003

Data Index: 19276 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2664. Min Act: -0.0003

Data Index: 1146376 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2765. Min Act: -0.0003

Data Index: 99545 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2702. Min Act: -0.0003

Data Index: 683618 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2580. Min Act: -0.0003

Data Index: 1020485 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2650. Min Act: -0.0003

Data Index: 34433 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2735. Min Act: -0.0004

Data Index: 239287 (C4 (Web Text))

Max Activating Token Index: 559