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

Dataset: The Pile

Neuron 3726 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: 0.8303. Min Range: -0.8303

Max Act: 0.8191. Min Act: -0.0000

Data Index: 647764 (The Pile)

Max Activating Token Index: 699

Text #1

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1804676 (The Pile)

Max Activating Token Index: 759

Text #2

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7959. Min Act: -0.0000

Data Index: 612885 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7747. Min Act: -0.0000

Data Index: 1810453 (The Pile)

Max Activating Token Index: 272

Text #4

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1447362 (The Pile)

Max Activating Token Index: 442

Text #5

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7905. Min Act: -0.0000

Data Index: 1527836 (The Pile)

Max Activating Token Index: 246

Text #6

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7786. Min Act: -0.0000

Data Index: 614001 (The Pile)

Max Activating Token Index: 208

Text #7

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7772. Min Act: -0.0000

Data Index: 25717 (The Pile)

Max Activating Token Index: 192

Text #8

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7571. Min Act: -0.0000

Data Index: 82660 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6936. Min Act: -0.0000

Data Index: 48200 (The Pile)

Max Activating Token Index: 491

Text #10

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7426. Min Act: -0.0000

Data Index: 274330 (The Pile)

Max Activating Token Index: 651

Text #11

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7389. Min Act: -0.0000

Data Index: 1982798 (The Pile)

Max Activating Token Index: 108

Text #12

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1541377 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7631. Min Act: -0.0000

Data Index: 1013068 (The Pile)

Max Activating Token Index: 1007

Text #14

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7994. Min Act: -0.0000

Data Index: 84060 (The Pile)

Max Activating Token Index: 464

Text #15

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7484. Min Act: -0.0000

Data Index: 1450832 (The Pile)

Max Activating Token Index: 439

Text #16

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1613785 (The Pile)

Max Activating Token Index: 362

Text #17

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7324. Min Act: -0.0000

Data Index: 1598419 (The Pile)

Max Activating Token Index: 82

Text #18

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7726. Min Act: -0.0000

Data Index: 1659414 (The Pile)

Max Activating Token Index: 519

Text #19

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1741566 (The Pile)

Max Activating Token Index: 701