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

Dataset: The Pile

Neuron 3070 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: 0.6237. Min Range: -0.6237

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1353227 (The Pile)

Max Activating Token Index: 546

Text #1

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5555. Min Act: -0.0000

Data Index: 841764 (The Pile)

Max Activating Token Index: 852

Text #2

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5035. Min Act: -0.0000

Data Index: 628797 (The Pile)

Max Activating Token Index: 126

Text #3

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4851. Min Act: -0.0000

Data Index: 1138365 (The Pile)

Max Activating Token Index: 636

Text #4

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5227. Min Act: -0.0000

Data Index: 230343 (The Pile)

Max Activating Token Index: 147

Text #5

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4814. Min Act: -0.0000

Data Index: 1932562 (The Pile)

Max Activating Token Index: 144

Text #6

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4876. Min Act: -0.0000

Data Index: 1566717 (The Pile)

Max Activating Token Index: 17

Text #7

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4678. Min Act: -0.0000

Data Index: 125954 (The Pile)

Max Activating Token Index: 331

Text #8

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4487. Min Act: -0.0000

Data Index: 95384 (The Pile)

Max Activating Token Index: 59

Text #9

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4607. Min Act: -0.0000

Data Index: 402214 (The Pile)

Max Activating Token Index: 174

Text #10

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4802. Min Act: -0.0000

Data Index: 19341 (The Pile)

Max Activating Token Index: 487

Text #11

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4743. Min Act: -0.0000

Data Index: 783696 (The Pile)

Max Activating Token Index: 859

Text #12

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4573. Min Act: -0.0000

Data Index: 828513 (The Pile)

Max Activating Token Index: 742

Text #13

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4993. Min Act: -0.0000

Data Index: 64527 (The Pile)

Max Activating Token Index: 976

Text #14

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4660. Min Act: -0.0000

Data Index: 1099114 (The Pile)

Max Activating Token Index: 577

Text #15

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1355614 (The Pile)

Max Activating Token Index: 45

Text #16

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4760. Min Act: -0.0000

Data Index: 1603260 (The Pile)

Max Activating Token Index: 919

Text #17

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4567. Min Act: -0.0000

Data Index: 128674 (The Pile)

Max Activating Token Index: 231

Text #18

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1112259 (The Pile)

Max Activating Token Index: 34

Text #19

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1401115 (The Pile)

Max Activating Token Index: 564