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

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

Neuron 4622 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3818. Min Act: -0.0003

Data Index: 1149621 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3679. Min Act: -0.0003

Data Index: 1152443 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3439. Min Act: -0.0003

Data Index: 194094 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3502. Min Act: -0.0003

Data Index: 504216 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3422. Min Act: -0.0002

Data Index: 1470109 (Python Code)

Max Activating Token Index: 448

Text #5

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3188. Min Act: -0.0003

Data Index: 1206641 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2887. Min Act: -0.0003

Data Index: 645294 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2867. Min Act: -0.0002

Data Index: 731788 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2971. Min Act: -0.0003

Data Index: 271026 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2830. Min Act: -0.0003

Data Index: 17438 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2991. Min Act: -0.0003

Data Index: 926465 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2876. Min Act: -0.0003

Data Index: 361173 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2971. Min Act: -0.0002

Data Index: 199783 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2640. Min Act: -0.0003

Data Index: 827138 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2598. Min Act: -0.0003

Data Index: 463737 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2744. Min Act: -0.0003

Data Index: 1099322 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2702. Min Act: -0.0003

Data Index: 27448 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2779. Min Act: -0.0003

Data Index: 1543445 (Python Code)

Max Activating Token Index: 500

Text #18

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2569. Min Act: -0.0003

Data Index: 120903 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2565. Min Act: -0.0003

Data Index: 519281 (C4 (Web Text))

Max Activating Token Index: 355