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

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

Neuron 57 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0690. Min Act: -0.0003

Data Index: 209413 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0670. Min Act: -0.0003

Data Index: 711555 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0594. Min Act: -0.0003

Data Index: 1073559 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0577. Min Act: -0.0003

Data Index: 385860 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0574. Min Act: -0.0003

Data Index: 423662 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0594. Min Act: -0.0003

Data Index: 55084 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0529. Min Act: -0.0003

Data Index: 379019 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0536. Min Act: -0.0003

Data Index: 634115 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0546. Min Act: -0.0004

Data Index: 217076 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0519. Min Act: -0.0003

Data Index: 859162 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0496. Min Act: -0.0003

Data Index: 569009 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0513. Min Act: -0.0004

Data Index: 94702 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0517. Min Act: -0.0004

Data Index: 543593 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0539. Min Act: -0.0003

Data Index: 576780 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0494. Min Act: -0.0003

Data Index: 554703 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0471. Min Act: -0.0003

Data Index: 419802 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0507. Min Act: -0.0004

Data Index: 600336 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1054068 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0478. Min Act: -0.0003

Data Index: 941790 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0482. Min Act: -0.0003

Data Index: 700667 (C4 (Web Text))

Max Activating Token Index: 971