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

Dataset: The Pile

Neuron 4001 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1041144 (The Pile)

Max Activating Token Index: 521

Text #1

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.9314. Min Act: -0.0000

Data Index: 829850 (The Pile)

Max Activating Token Index: 219

Text #2

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.8574. Min Act: -0.0000

Data Index: 1376855 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.8011. Min Act: -0.0000

Data Index: 80595 (The Pile)

Max Activating Token Index: 819

Text #4

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.7521. Min Act: -0.0000

Data Index: 1247455 (The Pile)

Max Activating Token Index: 191

Text #5

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.7479. Min Act: -0.0000

Data Index: 525335 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.7183. Min Act: -0.0000

Data Index: 42400 (The Pile)

Max Activating Token Index: 527

Text #7

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.7543. Min Act: -0.0000

Data Index: 106293 (The Pile)

Max Activating Token Index: 68

Text #8

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1463432 (The Pile)

Max Activating Token Index: 224

Text #9

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1898553 (The Pile)

Max Activating Token Index: 320

Text #10

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1168789 (The Pile)

Max Activating Token Index: 419

Text #11

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.7037. Min Act: -0.0000

Data Index: 1608709 (The Pile)

Max Activating Token Index: 709

Text #12

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.6812. Min Act: -0.0000

Data Index: 1667481 (The Pile)

Max Activating Token Index: 658

Text #13

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.6692. Min Act: -0.0000

Data Index: 280670 (The Pile)

Max Activating Token Index: 242

Text #14

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.5848. Min Act: -0.0000

Data Index: 894134 (The Pile)

Max Activating Token Index: 325

Text #15

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.5818. Min Act: -0.0000

Data Index: 835573 (The Pile)

Max Activating Token Index: 958

Text #16

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.7246. Min Act: -0.0000

Data Index: 1402292 (The Pile)

Max Activating Token Index: 947

Text #17

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.6173. Min Act: -0.0000

Data Index: 355860 (The Pile)

Max Activating Token Index: 92

Text #18

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1983277 (The Pile)

Max Activating Token Index: 584

Text #19

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.5865. Min Act: -0.0000

Data Index: 1285926 (The Pile)

Max Activating Token Index: 906