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

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

Neuron 2758 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: 0.0735. Min Range: -0.0735

Max Act: 0.0735. Min Act: -0.0002

Data Index: 500676 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0684. Min Act: -0.0002

Data Index: 193455 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0717. Min Act: -0.0002

Data Index: 1221561 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0565. Min Act: -0.0002

Data Index: 195305 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1181670 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0639. Min Act: -0.0002

Data Index: 384922 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0634. Min Act: -0.0002

Data Index: 933053 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0650. Min Act: -0.0002

Data Index: 579766 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0582. Min Act: -0.0002

Data Index: 849567 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0543. Min Act: -0.0002

Data Index: 286688 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0560. Min Act: -0.0002

Data Index: 194697 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0584. Min Act: -0.0002

Data Index: 65379 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0506. Min Act: -0.0002

Data Index: 148326 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0493. Min Act: -0.0002

Data Index: 257866 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1325332 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0640. Min Act: -0.0002

Data Index: 880610 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0531. Min Act: -0.0002

Data Index: 210930 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0593. Min Act: -0.0002

Data Index: 469523 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1300306 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1189463 (C4 (Web Text))

Max Activating Token Index: 93