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

Dataset: The Pile

Neuron 3036 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3356. Min Act: -0.0000

Data Index: 754968 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3460. Min Act: -0.0000

Data Index: 185844 (The Pile)

Max Activating Token Index: 890

Text #2

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3284. Min Act: -0.0000

Data Index: 586062 (The Pile)

Max Activating Token Index: 573

Text #3

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3141. Min Act: -0.0000

Data Index: 790044 (The Pile)

Max Activating Token Index: 202

Text #4

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3111. Min Act: -0.0000

Data Index: 569245 (The Pile)

Max Activating Token Index: 920

Text #5

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3012. Min Act: -0.0000

Data Index: 418484 (The Pile)

Max Activating Token Index: 976

Text #6

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2776. Min Act: -0.0000

Data Index: 575990 (The Pile)

Max Activating Token Index: 717

Text #7

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1028184 (The Pile)

Max Activating Token Index: 840

Text #8

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3043. Min Act: -0.0000

Data Index: 772248 (The Pile)

Max Activating Token Index: 124

Text #9

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3064. Min Act: -0.0000

Data Index: 1158311 (The Pile)

Max Activating Token Index: 753

Text #10

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2820. Min Act: 0.0000

Data Index: 248456 (The Pile)

Max Activating Token Index: 292

Text #11

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2664. Min Act: -0.0000

Data Index: 301926 (The Pile)

Max Activating Token Index: 117

Text #12

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2734. Min Act: -0.0000

Data Index: 735039 (The Pile)

Max Activating Token Index: 394

Text #13

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2723. Min Act: -0.0000

Data Index: 863565 (The Pile)

Max Activating Token Index: 79

Text #14

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2514. Min Act: -0.0000

Data Index: 411209 (The Pile)

Max Activating Token Index: 866

Text #15

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2618. Min Act: 0.0000

Data Index: 1023479 (The Pile)

Max Activating Token Index: 748

Text #16

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2374. Min Act: -0.0000

Data Index: 1594661 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2500. Min Act: -0.0000

Data Index: 1276825 (The Pile)

Max Activating Token Index: 632

Text #18

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2284. Min Act: -0.0000

Data Index: 189628 (The Pile)

Max Activating Token Index: 827

Text #19

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1733819 (The Pile)

Max Activating Token Index: 146