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

Dataset: The Pile

Neuron 4021 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.4516. Min Act: -0.0000

Data Index: 1390056 (The Pile)

Max Activating Token Index: 63

Text #1

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.3022. Min Act: -0.0000

Data Index: 1666988 (The Pile)

Max Activating Token Index: 230

Text #2

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.4618. Min Act: -0.0000

Data Index: 1708663 (The Pile)

Max Activating Token Index: 226

Text #3

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.3091. Min Act: -0.0000

Data Index: 849863 (The Pile)

Max Activating Token Index: 573

Text #4

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.3895. Min Act: -0.0000

Data Index: 1322171 (The Pile)

Max Activating Token Index: 198

Text #5

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.3716. Min Act: -0.0000

Data Index: 86732 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.2889. Min Act: -0.0000

Data Index: 307466 (The Pile)

Max Activating Token Index: 142

Text #7

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.2746. Min Act: -0.0000

Data Index: 23051 (The Pile)

Max Activating Token Index: 241

Text #8

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.1541. Min Act: -0.0000

Data Index: 1298057 (The Pile)

Max Activating Token Index: 639

Text #9

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.1936. Min Act: -0.0000

Data Index: 1595523 (The Pile)

Max Activating Token Index: 911

Text #10

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.0258. Min Act: -0.0000

Data Index: 437133 (The Pile)

Max Activating Token Index: 829

Text #11

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.0968. Min Act: -0.0000

Data Index: 1077880 (The Pile)

Max Activating Token Index: 131

Text #12

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.1850. Min Act: -0.0000

Data Index: 674534 (The Pile)

Max Activating Token Index: 227

Text #13

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.1485. Min Act: -0.0000

Data Index: 1022007 (The Pile)

Max Activating Token Index: 316

Text #14

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.2033. Min Act: -0.0000

Data Index: 877715 (The Pile)

Max Activating Token Index: 287

Text #15

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.1557. Min Act: -0.0000

Data Index: 1130906 (The Pile)

Max Activating Token Index: 729

Text #16

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.2189. Min Act: -0.0000

Data Index: 1365183 (The Pile)

Max Activating Token Index: 155

Text #17

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.0159. Min Act: -0.0000

Data Index: 707651 (The Pile)

Max Activating Token Index: 929

Text #18

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.0378. Min Act: -0.0000

Data Index: 551859 (The Pile)

Max Activating Token Index: 611

Text #19

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.0955. Min Act: -0.0000

Data Index: 255563 (The Pile)

Max Activating Token Index: 460