Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2892 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.9723. Min Act: -0.0000

Data Index: 21079 (The Pile)

Max Activating Token Index: 323

Text #1

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.9858. Min Act: -0.0000

Data Index: 772245 (The Pile)

Max Activating Token Index: 457

Text #2

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.8762. Min Act: -0.0000

Data Index: 984464 (The Pile)

Max Activating Token Index: 720

Text #3

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.9466. Min Act: -0.0000

Data Index: 731636 (The Pile)

Max Activating Token Index: 164

Text #4

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.9541. Min Act: -0.0000

Data Index: 1604704 (The Pile)

Max Activating Token Index: 354

Text #5

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.8816. Min Act: -0.0000

Data Index: 1953414 (The Pile)

Max Activating Token Index: 668

Text #6

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.7848. Min Act: -0.0000

Data Index: 1593325 (The Pile)

Max Activating Token Index: 143

Text #7

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.9066. Min Act: -0.0000

Data Index: 1593044 (The Pile)

Max Activating Token Index: 172

Text #8

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.9733. Min Act: -0.0000

Data Index: 1082488 (The Pile)

Max Activating Token Index: 486

Text #9

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.8548. Min Act: -0.0000

Data Index: 219041 (The Pile)

Max Activating Token Index: 904

Text #10

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.8509. Min Act: -0.0000

Data Index: 199638 (The Pile)

Max Activating Token Index: 576

Text #11

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.8654. Min Act: -0.0000

Data Index: 1234807 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.8615. Min Act: -0.0000

Data Index: 1480834 (The Pile)

Max Activating Token Index: 333

Text #13

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.8447. Min Act: -0.0000

Data Index: 652168 (The Pile)

Max Activating Token Index: 341

Text #14

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.7137. Min Act: -0.0000

Data Index: 1986076 (The Pile)

Max Activating Token Index: 811

Text #15

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.7467. Min Act: -0.0000

Data Index: 414105 (The Pile)

Max Activating Token Index: 206

Text #16

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.9211. Min Act: -0.0000

Data Index: 1183075 (The Pile)

Max Activating Token Index: 209

Text #17

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.7706. Min Act: -0.0000

Data Index: 572621 (The Pile)

Max Activating Token Index: 515

Text #18

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.5881. Min Act: -0.0000

Data Index: 199835 (The Pile)

Max Activating Token Index: 610

Text #19

Max Range: 1.9858. Min Range: -1.9858

Max Act: 1.7616. Min Act: -0.0000

Data Index: 338815 (The Pile)

Max Activating Token Index: 942