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

Dataset: The Pile

Neuron 3550 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.7607. Min Act: -0.0000

Data Index: 302208 (The Pile)

Max Activating Token Index: 652

Text #1

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.6433. Min Act: -0.0000

Data Index: 208998 (The Pile)

Max Activating Token Index: 358

Text #2

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.6857. Min Act: -0.0000

Data Index: 1072076 (The Pile)

Max Activating Token Index: 438

Text #3

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.0723. Min Act: 0.0000

Data Index: 1067340 (The Pile)

Max Activating Token Index: 914

Text #4

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.2370. Min Act: -0.0000

Data Index: 1781815 (The Pile)

Max Activating Token Index: 250

Text #5

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.2959. Min Act: -0.0000

Data Index: 1258798 (The Pile)

Max Activating Token Index: 382

Text #6

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.1496. Min Act: -0.0000

Data Index: 924345 (The Pile)

Max Activating Token Index: 565

Text #7

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.1487. Min Act: -0.0000

Data Index: 103931 (The Pile)

Max Activating Token Index: 741

Text #8

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.1093. Min Act: -0.0000

Data Index: 1390720 (The Pile)

Max Activating Token Index: 505

Text #9

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.0359. Min Act: -0.0000

Data Index: 1771814 (The Pile)

Max Activating Token Index: 698

Text #10

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.1007. Min Act: -0.0000

Data Index: 1434391 (The Pile)

Max Activating Token Index: 804

Text #11

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.0384. Min Act: -0.0000

Data Index: 1880339 (The Pile)

Max Activating Token Index: 53

Text #12

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.0049. Min Act: -0.0000

Data Index: 1647042 (The Pile)

Max Activating Token Index: 1006

Text #13

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.2466. Min Act: -0.0000

Data Index: 337594 (The Pile)

Max Activating Token Index: 993

Text #14

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.0704. Min Act: -0.0000

Data Index: 267085 (The Pile)

Max Activating Token Index: 410

Text #15

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.0650. Min Act: -0.0000

Data Index: 1824391 (The Pile)

Max Activating Token Index: 595

Text #16

Max Range: 1.7607. Min Range: -1.7607

Max Act: 0.9928. Min Act: -0.0000

Data Index: 1458816 (The Pile)

Max Activating Token Index: 583

Text #17

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.0971. Min Act: -0.0000

Data Index: 1900125 (The Pile)

Max Activating Token Index: 303

Text #18

Max Range: 1.7607. Min Range: -1.7607

Max Act: 0.9780. Min Act: -0.0000

Data Index: 974785 (The Pile)

Max Activating Token Index: 728

Text #19

Max Range: 1.7607. Min Range: -1.7607

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1392267 (The Pile)

Max Activating Token Index: 532