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

Dataset: The Pile

Neuron 494 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1427112 (The Pile)

Max Activating Token Index: 839

Text #1

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5894. Min Act: -0.0000

Data Index: 737421 (The Pile)

Max Activating Token Index: 396

Text #2

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.6475. Min Act: -0.0000

Data Index: 1033881 (The Pile)

Max Activating Token Index: 522

Text #3

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5181. Min Act: -0.0000

Data Index: 772659 (The Pile)

Max Activating Token Index: 246

Text #4

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1367036 (The Pile)

Max Activating Token Index: 570

Text #5

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5078. Min Act: -0.0000

Data Index: 103464 (The Pile)

Max Activating Token Index: 959

Text #6

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1568198 (The Pile)

Max Activating Token Index: 318

Text #7

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5671. Min Act: -0.0000

Data Index: 1473481 (The Pile)

Max Activating Token Index: 333

Text #8

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.6354. Min Act: -0.0000

Data Index: 1863950 (The Pile)

Max Activating Token Index: 782

Text #9

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5554. Min Act: -0.0000

Data Index: 314162 (The Pile)

Max Activating Token Index: 737

Text #10

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1094403 (The Pile)

Max Activating Token Index: 907

Text #11

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.4891. Min Act: -0.0000

Data Index: 83506 (The Pile)

Max Activating Token Index: 179

Text #12

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5543. Min Act: -0.0000

Data Index: 606813 (The Pile)

Max Activating Token Index: 604

Text #13

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1831576 (The Pile)

Max Activating Token Index: 673

Text #14

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5060. Min Act: -0.0000

Data Index: 897094 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5038. Min Act: -0.0000

Data Index: 955388 (The Pile)

Max Activating Token Index: 245

Text #16

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1189389 (The Pile)

Max Activating Token Index: 616

Text #17

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.4976. Min Act: -0.0000

Data Index: 326647 (The Pile)

Max Activating Token Index: 245

Text #18

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1609465 (The Pile)

Max Activating Token Index: 984

Text #19

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5246. Min Act: -0.0000

Data Index: 995512 (The Pile)

Max Activating Token Index: 992