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

Dataset: The Pile

Neuron 1834 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: 0.5960. Min Range: -0.5960

Max Act: 0.5960. Min Act: -0.0000

Data Index: 1835927 (The Pile)

Max Activating Token Index: 784

Text #1

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5694. Min Act: -0.0000

Data Index: 44326 (The Pile)

Max Activating Token Index: 716

Text #2

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1650499 (The Pile)

Max Activating Token Index: 336

Text #3

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1011422 (The Pile)

Max Activating Token Index: 769

Text #4

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4927. Min Act: -0.0000

Data Index: 618071 (The Pile)

Max Activating Token Index: 911

Text #5

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4421. Min Act: -0.0000

Data Index: 1769202 (The Pile)

Max Activating Token Index: 575

Text #6

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4312. Min Act: -0.0000

Data Index: 746124 (The Pile)

Max Activating Token Index: 559

Text #7

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1335273 (The Pile)

Max Activating Token Index: 539

Text #8

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1930594 (The Pile)

Max Activating Token Index: 680

Text #9

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1768769 (The Pile)

Max Activating Token Index: 585

Text #10

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4061. Min Act: -0.0000

Data Index: 1182902 (The Pile)

Max Activating Token Index: 561

Text #11

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1437146 (The Pile)

Max Activating Token Index: 663

Text #12

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.3820. Min Act: -0.0000

Data Index: 757924 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1156407 (The Pile)

Max Activating Token Index: 284

Text #14

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.3469. Min Act: -0.0000

Data Index: 1863682 (The Pile)

Max Activating Token Index: 774

Text #15

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.3914. Min Act: -0.0000

Data Index: 11441 (The Pile)

Max Activating Token Index: 439

Text #16

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1987409 (The Pile)

Max Activating Token Index: 770

Text #17

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.3870. Min Act: -0.0000

Data Index: 1850776 (The Pile)

Max Activating Token Index: 213

Text #18

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.3830. Min Act: -0.0000

Data Index: 610619 (The Pile)

Max Activating Token Index: 491

Text #19

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.3768. Min Act: 0.0000

Data Index: 907738 (The Pile)

Max Activating Token Index: 489