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

Dataset: The Pile

Neuron 408 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4351. Min Act: -0.0000

Data Index: 598050 (The Pile)

Max Activating Token Index: 862

Text #1

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4175. Min Act: -0.0000

Data Index: 60069 (The Pile)

Max Activating Token Index: 927

Text #2

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4034. Min Act: -0.0000

Data Index: 1621471 (The Pile)

Max Activating Token Index: 606

Text #3

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4437. Min Act: -0.0001

Data Index: 112814 (The Pile)

Max Activating Token Index: 747

Text #4

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3782. Min Act: -0.0000

Data Index: 343959 (The Pile)

Max Activating Token Index: 917

Text #5

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3397. Min Act: -0.0000

Data Index: 214677 (The Pile)

Max Activating Token Index: 671

Text #6

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1626361 (The Pile)

Max Activating Token Index: 554

Text #7

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3692. Min Act: -0.0000

Data Index: 1798920 (The Pile)

Max Activating Token Index: 738

Text #8

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3685. Min Act: -0.0000

Data Index: 1063994 (The Pile)

Max Activating Token Index: 194

Text #9

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3705. Min Act: -0.0000

Data Index: 1765367 (The Pile)

Max Activating Token Index: 1017

Text #10

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3501. Min Act: -0.0000

Data Index: 948961 (The Pile)

Max Activating Token Index: 205

Text #11

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3597. Min Act: -0.0000

Data Index: 901758 (The Pile)

Max Activating Token Index: 336

Text #12

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3486. Min Act: -0.0000

Data Index: 475886 (The Pile)

Max Activating Token Index: 146

Text #13

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3710. Min Act: -0.0000

Data Index: 1495535 (The Pile)

Max Activating Token Index: 619

Text #14

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3980. Min Act: -0.0001

Data Index: 377354 (The Pile)

Max Activating Token Index: 476

Text #15

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3741. Min Act: -0.0000

Data Index: 1240368 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3568. Min Act: -0.0000

Data Index: 98621 (The Pile)

Max Activating Token Index: 296

Text #17

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3685. Min Act: -0.0000

Data Index: 1639816 (The Pile)

Max Activating Token Index: 593

Text #18

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3688. Min Act: -0.0000

Data Index: 696836 (The Pile)

Max Activating Token Index: 401

Text #19

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3672. Min Act: -0.0000

Data Index: 42149 (The Pile)

Max Activating Token Index: 432