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

Dataset: The Pile

Neuron 4104 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0000

Data Index: 1344050 (The Pile)

Max Activating Token Index: 1

Text #1

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: 0.0000

Data Index: 20835 (The Pile)

Max Activating Token Index: 1

Text #2

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0000

Data Index: 1224726 (The Pile)

Max Activating Token Index: 1

Text #3

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: 0.0000

Data Index: 755552 (The Pile)

Max Activating Token Index: 1

Text #4

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0000

Data Index: 717375 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0000

Data Index: 1140276 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: 0.0000

Data Index: 1027105 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0000

Data Index: 971205 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0000

Data Index: 332183 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: 0.0000

Data Index: 701563 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0000

Data Index: 241009 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: 0.0000

Data Index: 1257684 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: 0.0000

Data Index: 217643 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0000

Data Index: 105708 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: 0.0000

Data Index: 317505 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0000

Data Index: 593783 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: 0.0000

Data Index: 814486 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: 0.0000

Data Index: 849029 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0000

Data Index: 163161 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: 0.0000

Data Index: 136687 (The Pile)

Max Activating Token Index: 1