Model: SoLU Model: 3 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-3l')

Text #0

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0815. Min Act: -0.0003

Data Index: 300670 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0600. Min Act: -0.0003

Data Index: 1291099 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0593. Min Act: -0.0003

Data Index: 789039 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1156840 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0599. Min Act: -0.0003

Data Index: 221453 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0564. Min Act: -0.0003

Data Index: 1319796 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0567. Min Act: -0.0003

Data Index: 391267 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0546. Min Act: -0.0003

Data Index: 792573 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0542. Min Act: -0.0003

Data Index: 170976 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0505. Min Act: -0.0002

Data Index: 269807 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0579. Min Act: -0.0003

Data Index: 1258935 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0540. Min Act: -0.0003

Data Index: 313281 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0536. Min Act: -0.0003

Data Index: 808640 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0528. Min Act: -0.0003

Data Index: 591278 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0537. Min Act: -0.0003

Data Index: 98151 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0523. Min Act: -0.0003

Data Index: 1000605 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0529. Min Act: -0.0003

Data Index: 392742 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1032611 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0508. Min Act: -0.0003

Data Index: 935036 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0503. Min Act: -0.0003

Data Index: 526857 (C4 (Web Text))

Max Activating Token Index: 118