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

Dataset: The Pile

Neuron 3403 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2808. Min Range: -1.2808

Max Act: 1.2808. Min Act: -0.0000

Data Index: 1307605 (The Pile)

Max Activating Token Index: 789

Text #1

Max Range: 1.2808. Min Range: -1.2808

Max Act: 1.2103. Min Act: -0.0000

Data Index: 747357 (The Pile)

Max Activating Token Index: 669

Text #2

Max Range: 1.2808. Min Range: -1.2808

Max Act: 1.1833. Min Act: -0.0000

Data Index: 803851 (The Pile)

Max Activating Token Index: 580

Text #3

Max Range: 1.2808. Min Range: -1.2808

Max Act: 1.0597. Min Act: -0.0000

Data Index: 1831445 (The Pile)

Max Activating Token Index: 218

Text #4

Max Range: 1.2808. Min Range: -1.2808

Max Act: 1.1076. Min Act: -0.0000

Data Index: 1218512 (The Pile)

Max Activating Token Index: 773

Text #5

Max Range: 1.2808. Min Range: -1.2808

Max Act: 1.0244. Min Act: -0.0000

Data Index: 1226015 (The Pile)

Max Activating Token Index: 274

Text #6

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.8773. Min Act: -0.0000

Data Index: 45445 (The Pile)

Max Activating Token Index: 631

Text #7

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.9248. Min Act: -0.0000

Data Index: 99364 (The Pile)

Max Activating Token Index: 266

Text #8

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.9127. Min Act: -0.0000

Data Index: 1548571 (The Pile)

Max Activating Token Index: 330

Text #9

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.9601. Min Act: -0.0000

Data Index: 423663 (The Pile)

Max Activating Token Index: 356

Text #10

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.8970. Min Act: 0.0000

Data Index: 1758262 (The Pile)

Max Activating Token Index: 809

Text #11

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.9520. Min Act: -0.0000

Data Index: 1230919 (The Pile)

Max Activating Token Index: 107

Text #12

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.9427. Min Act: -0.0000

Data Index: 193968 (The Pile)

Max Activating Token Index: 102

Text #13

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1259811 (The Pile)

Max Activating Token Index: 840

Text #14

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.8673. Min Act: -0.0000

Data Index: 1900325 (The Pile)

Max Activating Token Index: 233

Text #15

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1609347 (The Pile)

Max Activating Token Index: 533

Text #16

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.9184. Min Act: -0.0000

Data Index: 405255 (The Pile)

Max Activating Token Index: 85

Text #17

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.9081. Min Act: 0.0000

Data Index: 834546 (The Pile)

Max Activating Token Index: 88

Text #18

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.8514. Min Act: -0.0000

Data Index: 397458 (The Pile)

Max Activating Token Index: 364

Text #19

Max Range: 1.2808. Min Range: -1.2808

Max Act: 0.7883. Min Act: 0.0000

Data Index: 514970 (The Pile)

Max Activating Token Index: 285