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

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

Neuron 1562 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.1078. Min Act: -0.0002

Data Index: 344986 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0738. Min Act: -0.0002

Data Index: 622736 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0711. Min Act: -0.0002

Data Index: 353150 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0654. Min Act: -0.0002

Data Index: 87823 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0638. Min Act: -0.0002

Data Index: 674994 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0613. Min Act: -0.0002

Data Index: 129935 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0619. Min Act: -0.0002

Data Index: 892495 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0613. Min Act: -0.0002

Data Index: 814317 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0580. Min Act: -0.0002

Data Index: 344970 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1308893 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1326243 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0651. Min Act: -0.0002

Data Index: 821693 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0613. Min Act: -0.0002

Data Index: 281704 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1103208 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0552. Min Act: -0.0002

Data Index: 509692 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0584. Min Act: -0.0002

Data Index: 104920 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0607. Min Act: -0.0002

Data Index: 353107 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0588. Min Act: -0.0002

Data Index: 665149 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0607. Min Act: -0.0002

Data Index: 813738 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0582. Min Act: -0.0002

Data Index: 502420 (C4 (Web Text))

Max Activating Token Index: 294