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

Dataset: The Pile

Neuron 3022 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4820. Min Act: -0.0000

Data Index: 1977493 (The Pile)

Max Activating Token Index: 15

Text #1

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4542. Min Act: -0.0000

Data Index: 536134 (The Pile)

Max Activating Token Index: 1014

Text #2

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4670. Min Act: -0.0000

Data Index: 925575 (The Pile)

Max Activating Token Index: 500

Text #3

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4381. Min Act: -0.0000

Data Index: 836537 (The Pile)

Max Activating Token Index: 146

Text #4

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1194499 (The Pile)

Max Activating Token Index: 523

Text #5

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4157. Min Act: -0.0000

Data Index: 240073 (The Pile)

Max Activating Token Index: 526

Text #6

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4000. Min Act: -0.0000

Data Index: 577192 (The Pile)

Max Activating Token Index: 171

Text #7

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4100. Min Act: -0.0000

Data Index: 802772 (The Pile)

Max Activating Token Index: 984

Text #8

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3968. Min Act: -0.0000

Data Index: 62587 (The Pile)

Max Activating Token Index: 385

Text #9

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1869691 (The Pile)

Max Activating Token Index: 691

Text #10

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1564500 (The Pile)

Max Activating Token Index: 205

Text #11

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3528. Min Act: -0.0000

Data Index: 647157 (The Pile)

Max Activating Token Index: 598

Text #12

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3749. Min Act: -0.0000

Data Index: 721873 (The Pile)

Max Activating Token Index: 462

Text #13

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3700. Min Act: -0.0000

Data Index: 151590 (The Pile)

Max Activating Token Index: 13

Text #14

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1122627 (The Pile)

Max Activating Token Index: 19

Text #15

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3545. Min Act: -0.0000

Data Index: 572537 (The Pile)

Max Activating Token Index: 478

Text #16

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3411. Min Act: -0.0000

Data Index: 402201 (The Pile)

Max Activating Token Index: 210

Text #17

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1976292 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3570. Min Act: -0.0000

Data Index: 500822 (The Pile)

Max Activating Token Index: 475

Text #19

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3772. Min Act: -0.0000

Data Index: 1563170 (The Pile)

Max Activating Token Index: 648