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

Dataset: The Pile

Neuron 3776 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: 1.0398. Min Range: -1.0398

Max Act: 0.9484. Min Act: -0.0000

Data Index: 1843680 (The Pile)

Max Activating Token Index: 997

Text #1

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.8853. Min Act: -0.0000

Data Index: 1663762 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 1.0398. Min Range: -1.0398

Max Act: 1.0398. Min Act: -0.0000

Data Index: 1972834 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.9434. Min Act: -0.0000

Data Index: 1549967 (The Pile)

Max Activating Token Index: 312

Text #4

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7880. Min Act: -0.0000

Data Index: 1215211 (The Pile)

Max Activating Token Index: 464

Text #5

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7697. Min Act: -0.0000

Data Index: 490563 (The Pile)

Max Activating Token Index: 405

Text #6

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7525. Min Act: -0.0000

Data Index: 503925 (The Pile)

Max Activating Token Index: 478

Text #7

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1725141 (The Pile)

Max Activating Token Index: 747

Text #8

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.7542. Min Act: -0.0000

Data Index: 1264628 (The Pile)

Max Activating Token Index: 201

Text #9

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.6961. Min Act: -0.0000

Data Index: 1804462 (The Pile)

Max Activating Token Index: 482

Text #10

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1115571 (The Pile)

Max Activating Token Index: 413

Text #11

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.6322. Min Act: -0.0000

Data Index: 1031361 (The Pile)

Max Activating Token Index: 349

Text #12

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.6091. Min Act: -0.0000

Data Index: 204029 (The Pile)

Max Activating Token Index: 663

Text #13

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.6410. Min Act: -0.0000

Data Index: 1214620 (The Pile)

Max Activating Token Index: 203

Text #14

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1011521 (The Pile)

Max Activating Token Index: 161

Text #15

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1776603 (The Pile)

Max Activating Token Index: 236

Text #16

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1112149 (The Pile)

Max Activating Token Index: 70

Text #17

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.6127. Min Act: -0.0000

Data Index: 6048 (The Pile)

Max Activating Token Index: 982

Text #18

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1098754 (The Pile)

Max Activating Token Index: 832

Text #19

Max Range: 1.0398. Min Range: -1.0398

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1995567 (The Pile)

Max Activating Token Index: 148