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

Dataset: The Pile

Neuron 2057 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: 0.5022. Min Range: -0.5022

Max Act: 0.4972. Min Act: -0.0000

Data Index: 1871255 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.4604. Min Act: -0.0000

Data Index: 610016 (The Pile)

Max Activating Token Index: 802

Text #2

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1074161 (The Pile)

Max Activating Token Index: 310

Text #3

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.5022. Min Act: -0.0000

Data Index: 860004 (The Pile)

Max Activating Token Index: 872

Text #4

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1109954 (The Pile)

Max Activating Token Index: 983

Text #5

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.4323. Min Act: -0.0000

Data Index: 966391 (The Pile)

Max Activating Token Index: 821

Text #6

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.4408. Min Act: -0.0000

Data Index: 470751 (The Pile)

Max Activating Token Index: 887

Text #7

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1451669 (The Pile)

Max Activating Token Index: 964

Text #8

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3790. Min Act: -0.0000

Data Index: 664440 (The Pile)

Max Activating Token Index: 184

Text #9

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3860. Min Act: -0.0000

Data Index: 179643 (The Pile)

Max Activating Token Index: 558

Text #10

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1080106 (The Pile)

Max Activating Token Index: 905

Text #11

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.4004. Min Act: -0.0000

Data Index: 570594 (The Pile)

Max Activating Token Index: 636

Text #12

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.4037. Min Act: -0.0000

Data Index: 671853 (The Pile)

Max Activating Token Index: 593

Text #13

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3772. Min Act: -0.0000

Data Index: 1400935 (The Pile)

Max Activating Token Index: 827

Text #14

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3424. Min Act: -0.0000

Data Index: 1825304 (The Pile)

Max Activating Token Index: 893

Text #15

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3711. Min Act: -0.0000

Data Index: 1021247 (The Pile)

Max Activating Token Index: 507

Text #16

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3805. Min Act: -0.0000

Data Index: 1812746 (The Pile)

Max Activating Token Index: 326

Text #17

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3557. Min Act: -0.0000

Data Index: 165683 (The Pile)

Max Activating Token Index: 883

Text #18

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3638. Min Act: -0.0000

Data Index: 261011 (The Pile)

Max Activating Token Index: 980

Text #19

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3822. Min Act: -0.0000

Data Index: 1501656 (The Pile)

Max Activating Token Index: 206