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

Dataset: The Pile

Neuron 4986 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: 5.7353. Min Range: -5.7353

Max Act: 5.7353. Min Act: -0.0000

Data Index: 686933 (The Pile)

Max Activating Token Index: 569

Text #1

Max Range: 5.7353. Min Range: -5.7353

Max Act: 5.6703. Min Act: -0.0000

Data Index: 1190777 (The Pile)

Max Activating Token Index: 188

Text #2

Max Range: 5.7353. Min Range: -5.7353

Max Act: 5.7214. Min Act: -0.0000

Data Index: 538687 (The Pile)

Max Activating Token Index: 31

Text #3

Max Range: 5.7353. Min Range: -5.7353

Max Act: 4.9909. Min Act: -0.0000

Data Index: 1780781 (The Pile)

Max Activating Token Index: 423

Text #4

Max Range: 5.7353. Min Range: -5.7353

Max Act: 4.8044. Min Act: -0.0000

Data Index: 1591481 (The Pile)

Max Activating Token Index: 262

Text #5

Max Range: 5.7353. Min Range: -5.7353

Max Act: 4.4016. Min Act: -0.0000

Data Index: 1092783 (The Pile)

Max Activating Token Index: 294

Text #6

Max Range: 5.7353. Min Range: -5.7353

Max Act: 4.9304. Min Act: 0.0000

Data Index: 136700 (The Pile)

Max Activating Token Index: 877

Text #7

Max Range: 5.7353. Min Range: -5.7353

Max Act: 4.6325. Min Act: -0.0000

Data Index: 1968222 (The Pile)

Max Activating Token Index: 486

Text #8

Max Range: 5.7353. Min Range: -5.7353

Max Act: 4.4396. Min Act: -0.0000

Data Index: 211842 (The Pile)

Max Activating Token Index: 725

Text #9

Max Range: 5.7353. Min Range: -5.7353

Max Act: 4.6172. Min Act: -0.0000

Data Index: 1409327 (The Pile)

Max Activating Token Index: 722

Text #10

Max Range: 5.7353. Min Range: -5.7353

Max Act: 4.7052. Min Act: -0.0000

Data Index: 940523 (The Pile)

Max Activating Token Index: 547

Text #11

Max Range: 5.7353. Min Range: -5.7353

Max Act: 4.1150. Min Act: -0.0000

Data Index: 769316 (The Pile)

Max Activating Token Index: 646

Text #12

Max Range: 5.7353. Min Range: -5.7353

Max Act: 4.4364. Min Act: -0.0000

Data Index: 1098104 (The Pile)

Max Activating Token Index: 793

Text #13

Max Range: 5.7353. Min Range: -5.7353

Max Act: 4.1529. Min Act: -0.0000

Data Index: 691823 (The Pile)

Max Activating Token Index: 881

Text #14

Max Range: 5.7353. Min Range: -5.7353

Max Act: 4.1673. Min Act: -0.0000

Data Index: 875222 (The Pile)

Max Activating Token Index: 132

Text #15

Max Range: 5.7353. Min Range: -5.7353

Max Act: 4.5423. Min Act: -0.0000

Data Index: 1989458 (The Pile)

Max Activating Token Index: 758

Text #16

Max Range: 5.7353. Min Range: -5.7353

Max Act: 4.2570. Min Act: -0.0000

Data Index: 1514102 (The Pile)

Max Activating Token Index: 119

Text #17

Max Range: 5.7353. Min Range: -5.7353

Max Act: 4.0719. Min Act: -0.0000

Data Index: 98606 (The Pile)

Max Activating Token Index: 411

Text #18

Max Range: 5.7353. Min Range: -5.7353

Max Act: 4.2354. Min Act: -0.0000

Data Index: 289635 (The Pile)

Max Activating Token Index: 356

Text #19

Max Range: 5.7353. Min Range: -5.7353

Max Act: 4.1805. Min Act: -0.0000

Data Index: 1760404 (The Pile)

Max Activating Token Index: 685