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

Dataset: The Pile

Neuron 86 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5461. Min Range: -3.5461

Max Act: 3.5461. Min Act: -0.0000

Data Index: 1042201 (The Pile)

Max Activating Token Index: 787

Text #1

Max Range: 3.5461. Min Range: -3.5461

Max Act: 3.3835. Min Act: -0.0000

Data Index: 467961 (The Pile)

Max Activating Token Index: 138

Text #2

Max Range: 3.5461. Min Range: -3.5461

Max Act: 3.3548. Min Act: -0.0000

Data Index: 717405 (The Pile)

Max Activating Token Index: 575

Text #3

Max Range: 3.5461. Min Range: -3.5461

Max Act: 3.3301. Min Act: -0.0000

Data Index: 915664 (The Pile)

Max Activating Token Index: 537

Text #4

Max Range: 3.5461. Min Range: -3.5461

Max Act: 3.1430. Min Act: -0.0000

Data Index: 693649 (The Pile)

Max Activating Token Index: 993

Text #5

Max Range: 3.5461. Min Range: -3.5461

Max Act: 3.0711. Min Act: -0.0000

Data Index: 402337 (The Pile)

Max Activating Token Index: 1009

Text #6

Max Range: 3.5461. Min Range: -3.5461

Max Act: 3.0431. Min Act: -0.0000

Data Index: 1918761 (The Pile)

Max Activating Token Index: 199

Text #7

Max Range: 3.5461. Min Range: -3.5461

Max Act: 2.8285. Min Act: -0.0000

Data Index: 147825 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 3.5461. Min Range: -3.5461

Max Act: 2.9724. Min Act: -0.0000

Data Index: 1477677 (The Pile)

Max Activating Token Index: 343

Text #9

Max Range: 3.5461. Min Range: -3.5461

Max Act: 2.9553. Min Act: -0.0000

Data Index: 992681 (The Pile)

Max Activating Token Index: 625

Text #10

Max Range: 3.5461. Min Range: -3.5461

Max Act: 2.7849. Min Act: -0.0000

Data Index: 555731 (The Pile)

Max Activating Token Index: 48

Text #11

Max Range: 3.5461. Min Range: -3.5461

Max Act: 2.7633. Min Act: -0.0000

Data Index: 685629 (The Pile)

Max Activating Token Index: 167

Text #12

Max Range: 3.5461. Min Range: -3.5461

Max Act: 2.8656. Min Act: -0.0000

Data Index: 1624210 (The Pile)

Max Activating Token Index: 532

Text #13

Max Range: 3.5461. Min Range: -3.5461

Max Act: 2.6656. Min Act: -0.0000

Data Index: 533593 (The Pile)

Max Activating Token Index: 338

Text #14

Max Range: 3.5461. Min Range: -3.5461

Max Act: 2.7859. Min Act: -0.0000

Data Index: 1792601 (The Pile)

Max Activating Token Index: 1019

Text #15

Max Range: 3.5461. Min Range: -3.5461

Max Act: 2.6600. Min Act: -0.0000

Data Index: 443137 (The Pile)

Max Activating Token Index: 638

Text #16

Max Range: 3.5461. Min Range: -3.5461

Max Act: 2.6454. Min Act: -0.0000

Data Index: 1726877 (The Pile)

Max Activating Token Index: 898

Text #17

Max Range: 3.5461. Min Range: -3.5461

Max Act: 2.6515. Min Act: -0.0000

Data Index: 1646828 (The Pile)

Max Activating Token Index: 794

Text #18

Max Range: 3.5461. Min Range: -3.5461

Max Act: 2.6221. Min Act: 0.0000

Data Index: 1619812 (The Pile)

Max Activating Token Index: 261

Text #19

Max Range: 3.5461. Min Range: -3.5461

Max Act: 2.6109. Min Act: 0.0000

Data Index: 171932 (The Pile)

Max Activating Token Index: 562