Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2315 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6540. Min Act: -0.0002

Data Index: 59919 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.7027. Min Act: -0.0002

Data Index: 130225 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.7227. Min Act: -0.0001

Data Index: 1192613 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.7432. Min Act: -0.0002

Data Index: 454715 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6685. Min Act: -0.0002

Data Index: 81367 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6595. Min Act: -0.0002

Data Index: 1094603 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6761. Min Act: -0.0002

Data Index: 45653 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6457. Min Act: -0.0002

Data Index: 362599 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6676. Min Act: -0.0002

Data Index: 868145 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6222. Min Act: -0.0002

Data Index: 770662 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.7248. Min Act: -0.0001

Data Index: 387288 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6620. Min Act: -0.0001

Data Index: 1118622 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6562. Min Act: -0.0001

Data Index: 974858 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6671. Min Act: -0.0001

Data Index: 584511 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6733. Min Act: -0.0002

Data Index: 175910 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5734. Min Act: -0.0002

Data Index: 365662 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6552. Min Act: -0.0001

Data Index: 792530 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6383. Min Act: -0.0002

Data Index: 222503 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.5950. Min Act: -0.0001

Data Index: 1247323 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.7432. Min Range: -0.7432

Max Act: 0.6462. Min Act: -0.0001

Data Index: 637571 (C4 (Web Text))

Max Activating Token Index: 145