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

Dataset: The Pile

Neuron 3793 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3159. Min Range: -4.3159

Max Act: 4.3159. Min Act: -0.0000

Data Index: 1748472 (The Pile)

Max Activating Token Index: 282

Text #1

Max Range: 4.3159. Min Range: -4.3159

Max Act: 3.8245. Min Act: -0.0000

Data Index: 427008 (The Pile)

Max Activating Token Index: 533

Text #2

Max Range: 4.3159. Min Range: -4.3159

Max Act: 3.4883. Min Act: -0.0000

Data Index: 789596 (The Pile)

Max Activating Token Index: 579

Text #3

Max Range: 4.3159. Min Range: -4.3159

Max Act: 3.4488. Min Act: -0.0000

Data Index: 935825 (The Pile)

Max Activating Token Index: 238

Text #4

Max Range: 4.3159. Min Range: -4.3159

Max Act: 3.5914. Min Act: -0.0000

Data Index: 383883 (The Pile)

Max Activating Token Index: 510

Text #5

Max Range: 4.3159. Min Range: -4.3159

Max Act: 3.3540. Min Act: -0.0000

Data Index: 1176243 (The Pile)

Max Activating Token Index: 501

Text #6

Max Range: 4.3159. Min Range: -4.3159

Max Act: 3.4853. Min Act: -0.0000

Data Index: 686922 (The Pile)

Max Activating Token Index: 695

Text #7

Max Range: 4.3159. Min Range: -4.3159

Max Act: 3.4526. Min Act: -0.0000

Data Index: 767679 (The Pile)

Max Activating Token Index: 597

Text #8

Max Range: 4.3159. Min Range: -4.3159

Max Act: 3.4386. Min Act: -0.0000

Data Index: 1065174 (The Pile)

Max Activating Token Index: 458

Text #9

Max Range: 4.3159. Min Range: -4.3159

Max Act: 3.2600. Min Act: -0.0000

Data Index: 1234241 (The Pile)

Max Activating Token Index: 637

Text #10

Max Range: 4.3159. Min Range: -4.3159

Max Act: 3.4253. Min Act: -0.0000

Data Index: 751739 (The Pile)

Max Activating Token Index: 537

Text #11

Max Range: 4.3159. Min Range: -4.3159

Max Act: 3.2805. Min Act: -0.0000

Data Index: 476454 (The Pile)

Max Activating Token Index: 113

Text #12

Max Range: 4.3159. Min Range: -4.3159

Max Act: 3.4052. Min Act: -0.0000

Data Index: 1481069 (The Pile)

Max Activating Token Index: 351

Text #13

Max Range: 4.3159. Min Range: -4.3159

Max Act: 3.0790. Min Act: -0.0000

Data Index: 666249 (The Pile)

Max Activating Token Index: 282

Text #14

Max Range: 4.3159. Min Range: -4.3159

Max Act: 3.2122. Min Act: -0.0000

Data Index: 1617895 (The Pile)

Max Activating Token Index: 479

Text #15

Max Range: 4.3159. Min Range: -4.3159

Max Act: 3.5068. Min Act: -0.0000

Data Index: 110939 (The Pile)

Max Activating Token Index: 328

Text #16

Max Range: 4.3159. Min Range: -4.3159

Max Act: 3.2210. Min Act: -0.0000

Data Index: 961524 (The Pile)

Max Activating Token Index: 263

Text #17

Max Range: 4.3159. Min Range: -4.3159

Max Act: 3.2235. Min Act: -0.0000

Data Index: 565334 (The Pile)

Max Activating Token Index: 450

Text #18

Max Range: 4.3159. Min Range: -4.3159

Max Act: 3.3557. Min Act: -0.0000

Data Index: 1433707 (The Pile)

Max Activating Token Index: 600

Text #19

Max Range: 4.3159. Min Range: -4.3159

Max Act: 3.3360. Min Act: -0.0000

Data Index: 1433046 (The Pile)

Max Activating Token Index: 455