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

Dataset: The Pile

Neuron 1577 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1601045 (The Pile)

Max Activating Token Index: 332

Text #1

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.5463. Min Act: -0.0000

Data Index: 1409545 (The Pile)

Max Activating Token Index: 354

Text #2

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1513198 (The Pile)

Max Activating Token Index: 688

Text #3

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.5430. Min Act: -0.0000

Data Index: 200140 (The Pile)

Max Activating Token Index: 378

Text #4

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.5971. Min Act: 0.0000

Data Index: 346965 (The Pile)

Max Activating Token Index: 919

Text #5

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.5567. Min Act: -0.0000

Data Index: 111875 (The Pile)

Max Activating Token Index: 294

Text #6

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.5770. Min Act: -0.0000

Data Index: 973353 (The Pile)

Max Activating Token Index: 476

Text #7

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1636185 (The Pile)

Max Activating Token Index: 318

Text #8

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1933576 (The Pile)

Max Activating Token Index: 141

Text #9

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.5312. Min Act: -0.0000

Data Index: 1039315 (The Pile)

Max Activating Token Index: 871

Text #10

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.5757. Min Act: -0.0000

Data Index: 1298215 (The Pile)

Max Activating Token Index: 938

Text #11

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.5353. Min Act: -0.0000

Data Index: 212795 (The Pile)

Max Activating Token Index: 221

Text #12

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1509160 (The Pile)

Max Activating Token Index: 959

Text #13

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1645510 (The Pile)

Max Activating Token Index: 797

Text #14

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.5346. Min Act: -0.0000

Data Index: 1072525 (The Pile)

Max Activating Token Index: 968

Text #15

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.5353. Min Act: -0.0000

Data Index: 558616 (The Pile)

Max Activating Token Index: 386

Text #16

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.5429. Min Act: -0.0000

Data Index: 644451 (The Pile)

Max Activating Token Index: 410

Text #17

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1470453 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.5052. Min Act: -0.0000

Data Index: 1157760 (The Pile)

Max Activating Token Index: 283

Text #19

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.4899. Min Act: -0.0000

Data Index: 1126796 (The Pile)

Max Activating Token Index: 107