Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3276 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.8001. Min Act: -0.0000

Data Index: 1003903 (The Pile)

Max Activating Token Index: 386

Text #1

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.5224. Min Act: -0.0000

Data Index: 391972 (The Pile)

Max Activating Token Index: 768

Text #2

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.4629. Min Act: -0.0000

Data Index: 1147819 (The Pile)

Max Activating Token Index: 798

Text #3

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.4050. Min Act: -0.0000

Data Index: 378236 (The Pile)

Max Activating Token Index: 143

Text #4

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.4155. Min Act: -0.0000

Data Index: 1041963 (The Pile)

Max Activating Token Index: 152

Text #5

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.3991. Min Act: -0.0000

Data Index: 1750156 (The Pile)

Max Activating Token Index: 694

Text #6

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.3796. Min Act: -0.0000

Data Index: 1689037 (The Pile)

Max Activating Token Index: 576

Text #7

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.4183. Min Act: -0.0000

Data Index: 901800 (The Pile)

Max Activating Token Index: 539

Text #8

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.3770. Min Act: -0.0000

Data Index: 1718777 (The Pile)

Max Activating Token Index: 307

Text #9

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.4114. Min Act: -0.0000

Data Index: 906947 (The Pile)

Max Activating Token Index: 184

Text #10

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.3295. Min Act: -0.0000

Data Index: 113203 (The Pile)

Max Activating Token Index: 214

Text #11

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.3281. Min Act: -0.0000

Data Index: 1080726 (The Pile)

Max Activating Token Index: 142

Text #12

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.2645. Min Act: -0.0000

Data Index: 914367 (The Pile)

Max Activating Token Index: 703

Text #13

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.2695. Min Act: -0.0000

Data Index: 189092 (The Pile)

Max Activating Token Index: 717

Text #14

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.3587. Min Act: -0.0000

Data Index: 670994 (The Pile)

Max Activating Token Index: 93

Text #15

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.2340. Min Act: -0.0000

Data Index: 1534722 (The Pile)

Max Activating Token Index: 875

Text #16

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.2668. Min Act: -0.0000

Data Index: 1258763 (The Pile)

Max Activating Token Index: 540

Text #17

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.3211. Min Act: -0.0000

Data Index: 1593555 (The Pile)

Max Activating Token Index: 741

Text #18

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.2935. Min Act: -0.0000

Data Index: 1936969 (The Pile)

Max Activating Token Index: 671

Text #19

Max Range: 1.8001. Min Range: -1.8001

Max Act: 1.2555. Min Act: -0.0000

Data Index: 1678726 (The Pile)

Max Activating Token Index: 60