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

Dataset: The Pile

Neuron 1721 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: 0.6076. Min Range: -0.6076

Max Act: 0.6076. Min Act: -0.0000

Data Index: 578564 (The Pile)

Max Activating Token Index: 81

Text #1

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1093869 (The Pile)

Max Activating Token Index: 817

Text #2

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1663265 (The Pile)

Max Activating Token Index: 619

Text #3

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4650. Min Act: -0.0000

Data Index: 253508 (The Pile)

Max Activating Token Index: 714

Text #4

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4689. Min Act: -0.0000

Data Index: 703199 (The Pile)

Max Activating Token Index: 513

Text #5

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.5154. Min Act: -0.0000

Data Index: 489185 (The Pile)

Max Activating Token Index: 77

Text #6

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1588740 (The Pile)

Max Activating Token Index: 489

Text #7

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1078062 (The Pile)

Max Activating Token Index: 233

Text #8

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1864623 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.3892. Min Act: -0.0000

Data Index: 1593199 (The Pile)

Max Activating Token Index: 796

Text #10

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.3968. Min Act: -0.0000

Data Index: 24628 (The Pile)

Max Activating Token Index: 307

Text #11

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4247. Min Act: -0.0000

Data Index: 1041264 (The Pile)

Max Activating Token Index: 541

Text #12

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1550862 (The Pile)

Max Activating Token Index: 49

Text #13

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4089. Min Act: -0.0000

Data Index: 333350 (The Pile)

Max Activating Token Index: 863

Text #14

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.3947. Min Act: -0.0000

Data Index: 1046877 (The Pile)

Max Activating Token Index: 731

Text #15

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.3867. Min Act: -0.0000

Data Index: 1793427 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.3892. Min Act: -0.0000

Data Index: 1219338 (The Pile)

Max Activating Token Index: 202

Text #17

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.3598. Min Act: -0.0000

Data Index: 775408 (The Pile)

Max Activating Token Index: 339

Text #18

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1421042 (The Pile)

Max Activating Token Index: 160

Text #19

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.3583. Min Act: -0.0000

Data Index: 720004 (The Pile)

Max Activating Token Index: 415