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

Dataset: The Pile

Neuron 3070 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: 0.8654. Min Range: -0.8654

Max Act: 0.8286. Min Act: -0.0000

Data Index: 1639980 (The Pile)

Max Activating Token Index: 694

Text #1

Max Range: 0.8654. Min Range: -0.8654

Max Act: 0.8654. Min Act: -0.0000

Data Index: 1486840 (The Pile)

Max Activating Token Index: 997

Text #2

Max Range: 0.8654. Min Range: -0.8654

Max Act: 0.6314. Min Act: -0.0000

Data Index: 686250 (The Pile)

Max Activating Token Index: 1012

Text #3

Max Range: 0.8654. Min Range: -0.8654

Max Act: 0.6477. Min Act: -0.0000

Data Index: 44372 (The Pile)

Max Activating Token Index: 933

Text #4

Max Range: 0.8654. Min Range: -0.8654

Max Act: 0.6561. Min Act: -0.0000

Data Index: 1114858 (The Pile)

Max Activating Token Index: 502

Text #5

Max Range: 0.8654. Min Range: -0.8654

Max Act: 0.5815. Min Act: -0.0000

Data Index: 352669 (The Pile)

Max Activating Token Index: 11

Text #6

Max Range: 0.8654. Min Range: -0.8654

Max Act: 0.5102. Min Act: -0.0000

Data Index: 439459 (The Pile)

Max Activating Token Index: 992

Text #7

Max Range: 0.8654. Min Range: -0.8654

Max Act: 0.5605. Min Act: -0.0000

Data Index: 1221143 (The Pile)

Max Activating Token Index: 303

Text #8

Max Range: 0.8654. Min Range: -0.8654

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1910791 (The Pile)

Max Activating Token Index: 640

Text #9

Max Range: 0.8654. Min Range: -0.8654

Max Act: 0.5857. Min Act: -0.0000

Data Index: 619754 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 0.8654. Min Range: -0.8654

Max Act: 0.5949. Min Act: -0.0000

Data Index: 267682 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 0.8654. Min Range: -0.8654

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1798075 (The Pile)

Max Activating Token Index: 737

Text #12

Max Range: 0.8654. Min Range: -0.8654

Max Act: 0.5075. Min Act: -0.0000

Data Index: 284733 (The Pile)

Max Activating Token Index: 545

Text #13

Max Range: 0.8654. Min Range: -0.8654

Max Act: 0.5499. Min Act: -0.0000

Data Index: 1657058 (The Pile)

Max Activating Token Index: 332

Text #14

Max Range: 0.8654. Min Range: -0.8654

Max Act: 0.5077. Min Act: -0.0000

Data Index: 115446 (The Pile)

Max Activating Token Index: 366

Text #15

Max Range: 0.8654. Min Range: -0.8654

Max Act: 0.4904. Min Act: -0.0000

Data Index: 389280 (The Pile)

Max Activating Token Index: 218

Text #16

Max Range: 0.8654. Min Range: -0.8654

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1638619 (The Pile)

Max Activating Token Index: 175

Text #17

Max Range: 0.8654. Min Range: -0.8654

Max Act: 0.5118. Min Act: -0.0000

Data Index: 218967 (The Pile)

Max Activating Token Index: 672

Text #18

Max Range: 0.8654. Min Range: -0.8654

Max Act: 0.4592. Min Act: -0.0000

Data Index: 157242 (The Pile)

Max Activating Token Index: 72

Text #19

Max Range: 0.8654. Min Range: -0.8654

Max Act: 0.4702. Min Act: -0.0000

Data Index: 35914 (The Pile)

Max Activating Token Index: 332