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

Dataset: The Pile

Neuron 143 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: 0.5647. Min Range: -0.5647

Max Act: 0.5497. Min Act: -0.0000

Data Index: 414906 (The Pile)

Max Activating Token Index: 163

Text #1

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.5647. Min Act: -0.0000

Data Index: 1995509 (The Pile)

Max Activating Token Index: 465

Text #2

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.5441. Min Act: -0.0000

Data Index: 578772 (The Pile)

Max Activating Token Index: 115

Text #3

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4608. Min Act: -0.0000

Data Index: 499249 (The Pile)

Max Activating Token Index: 241

Text #4

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4718. Min Act: -0.0000

Data Index: 102867 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1712520 (The Pile)

Max Activating Token Index: 375

Text #6

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4419. Min Act: 0.0000

Data Index: 867285 (The Pile)

Max Activating Token Index: 945

Text #7

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4561. Min Act: -0.0000

Data Index: 37610 (The Pile)

Max Activating Token Index: 149

Text #8

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4516. Min Act: 0.0000

Data Index: 536975 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4466. Min Act: -0.0000

Data Index: 443046 (The Pile)

Max Activating Token Index: 966

Text #10

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4260. Min Act: -0.0000

Data Index: 74099 (The Pile)

Max Activating Token Index: 628

Text #11

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1319686 (The Pile)

Max Activating Token Index: 851

Text #12

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4468. Min Act: -0.0000

Data Index: 682762 (The Pile)

Max Activating Token Index: 971

Text #13

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4059. Min Act: -0.0000

Data Index: 1327326 (The Pile)

Max Activating Token Index: 623

Text #14

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4592. Min Act: -0.0000

Data Index: 1689510 (The Pile)

Max Activating Token Index: 615

Text #15

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4317. Min Act: -0.0000

Data Index: 1415301 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4148. Min Act: -0.0000

Data Index: 1155111 (The Pile)

Max Activating Token Index: 191

Text #17

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4148. Min Act: -0.0000

Data Index: 5515 (The Pile)

Max Activating Token Index: 670

Text #18

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4070. Min Act: -0.0000

Data Index: 1503459 (The Pile)

Max Activating Token Index: 645

Text #19

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4106. Min Act: -0.0000

Data Index: 1525997 (The Pile)

Max Activating Token Index: 258