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

Dataset: The Pile

Neuron 4621 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0357. Min Range: -3.0357

Max Act: 3.0357. Min Act: -0.0000

Data Index: 1333220 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 3.0357. Min Range: -3.0357

Max Act: 2.6349. Min Act: -0.0000

Data Index: 927169 (The Pile)

Max Activating Token Index: 924

Text #2

Max Range: 3.0357. Min Range: -3.0357

Max Act: 2.0765. Min Act: -0.0000

Data Index: 473616 (The Pile)

Max Activating Token Index: 498

Text #3

Max Range: 3.0357. Min Range: -3.0357

Max Act: 1.8902. Min Act: -0.0000

Data Index: 316838 (The Pile)

Max Activating Token Index: 490

Text #4

Max Range: 3.0357. Min Range: -3.0357

Max Act: 1.8658. Min Act: -0.0000

Data Index: 1031485 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 3.0357. Min Range: -3.0357

Max Act: 1.9199. Min Act: -0.0000

Data Index: 1216008 (The Pile)

Max Activating Token Index: 176

Text #6

Max Range: 3.0357. Min Range: -3.0357

Max Act: 1.7816. Min Act: -0.0000

Data Index: 757777 (The Pile)

Max Activating Token Index: 514

Text #7

Max Range: 3.0357. Min Range: -3.0357

Max Act: 1.4146. Min Act: -0.0000

Data Index: 636198 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 3.0357. Min Range: -3.0357

Max Act: 1.7038. Min Act: -0.0000

Data Index: 1256668 (The Pile)

Max Activating Token Index: 745

Text #9

Max Range: 3.0357. Min Range: -3.0357

Max Act: 1.7440. Min Act: -0.0000

Data Index: 531745 (The Pile)

Max Activating Token Index: 462

Text #10

Max Range: 3.0357. Min Range: -3.0357

Max Act: 1.5534. Min Act: -0.0000

Data Index: 1707714 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 3.0357. Min Range: -3.0357

Max Act: 1.4682. Min Act: -0.0000

Data Index: 1564797 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 3.0357. Min Range: -3.0357

Max Act: 1.5531. Min Act: -0.0000

Data Index: 327978 (The Pile)

Max Activating Token Index: 410

Text #13

Max Range: 3.0357. Min Range: -3.0357

Max Act: 1.5395. Min Act: -0.0000

Data Index: 1709434 (The Pile)

Max Activating Token Index: 252

Text #14

Max Range: 3.0357. Min Range: -3.0357

Max Act: 1.6223. Min Act: -0.0000

Data Index: 1374892 (The Pile)

Max Activating Token Index: 411

Text #15

Max Range: 3.0357. Min Range: -3.0357

Max Act: 1.6123. Min Act: -0.0000

Data Index: 1052550 (The Pile)

Max Activating Token Index: 391

Text #16

Max Range: 3.0357. Min Range: -3.0357

Max Act: 1.5056. Min Act: -0.0000

Data Index: 1297476 (The Pile)

Max Activating Token Index: 151

Text #17

Max Range: 3.0357. Min Range: -3.0357

Max Act: 1.4977. Min Act: -0.0000

Data Index: 14787 (The Pile)

Max Activating Token Index: 208

Text #18

Max Range: 3.0357. Min Range: -3.0357

Max Act: 1.4071. Min Act: -0.0000

Data Index: 602690 (The Pile)

Max Activating Token Index: 262

Text #19

Max Range: 3.0357. Min Range: -3.0357

Max Act: 1.4602. Min Act: -0.0000

Data Index: 688005 (The Pile)

Max Activating Token Index: 765