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

Dataset: The Pile

Neuron 2922 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: 5.9630. Min Range: -5.9630

Max Act: 5.9630. Min Act: -0.0000

Data Index: 262828 (The Pile)

Max Activating Token Index: 759

Text #1

Max Range: 5.9630. Min Range: -5.9630

Max Act: 5.6386. Min Act: -0.0000

Data Index: 569043 (The Pile)

Max Activating Token Index: 1016

Text #2

Max Range: 5.9630. Min Range: -5.9630

Max Act: 5.2764. Min Act: -0.0000

Data Index: 1042254 (The Pile)

Max Activating Token Index: 478

Text #3

Max Range: 5.9630. Min Range: -5.9630

Max Act: 5.2145. Min Act: -0.0000

Data Index: 1193813 (The Pile)

Max Activating Token Index: 214

Text #4

Max Range: 5.9630. Min Range: -5.9630

Max Act: 5.1330. Min Act: -0.0000

Data Index: 1381133 (The Pile)

Max Activating Token Index: 529

Text #5

Max Range: 5.9630. Min Range: -5.9630

Max Act: 5.2624. Min Act: -0.0000

Data Index: 1189925 (The Pile)

Max Activating Token Index: 323

Text #6

Max Range: 5.9630. Min Range: -5.9630

Max Act: 5.2690. Min Act: -0.0000

Data Index: 1568618 (The Pile)

Max Activating Token Index: 675

Text #7

Max Range: 5.9630. Min Range: -5.9630

Max Act: 5.1939. Min Act: -0.0000

Data Index: 526632 (The Pile)

Max Activating Token Index: 834

Text #8

Max Range: 5.9630. Min Range: -5.9630

Max Act: 5.1499. Min Act: -0.0000

Data Index: 685415 (The Pile)

Max Activating Token Index: 588

Text #9

Max Range: 5.9630. Min Range: -5.9630

Max Act: 5.2991. Min Act: -0.0000

Data Index: 1366473 (The Pile)

Max Activating Token Index: 310

Text #10

Max Range: 5.9630. Min Range: -5.9630

Max Act: 4.8861. Min Act: -0.0000

Data Index: 1497988 (The Pile)

Max Activating Token Index: 330

Text #11

Max Range: 5.9630. Min Range: -5.9630

Max Act: 5.0440. Min Act: -0.0000

Data Index: 1079178 (The Pile)

Max Activating Token Index: 135

Text #12

Max Range: 5.9630. Min Range: -5.9630

Max Act: 5.0081. Min Act: -0.0000

Data Index: 299571 (The Pile)

Max Activating Token Index: 370

Text #13

Max Range: 5.9630. Min Range: -5.9630

Max Act: 5.1878. Min Act: -0.0000

Data Index: 572059 (The Pile)

Max Activating Token Index: 512

Text #14

Max Range: 5.9630. Min Range: -5.9630

Max Act: 4.9918. Min Act: -0.0000

Data Index: 1826116 (The Pile)

Max Activating Token Index: 173

Text #15

Max Range: 5.9630. Min Range: -5.9630

Max Act: 4.8091. Min Act: -0.0000

Data Index: 1911692 (The Pile)

Max Activating Token Index: 477

Text #16

Max Range: 5.9630. Min Range: -5.9630

Max Act: 4.7515. Min Act: -0.0000

Data Index: 1185178 (The Pile)

Max Activating Token Index: 896

Text #17

Max Range: 5.9630. Min Range: -5.9630

Max Act: 5.0722. Min Act: -0.0000

Data Index: 1299832 (The Pile)

Max Activating Token Index: 976

Text #18

Max Range: 5.9630. Min Range: -5.9630

Max Act: 4.8722. Min Act: -0.0000

Data Index: 271872 (The Pile)

Max Activating Token Index: 761

Text #19

Max Range: 5.9630. Min Range: -5.9630

Max Act: 4.8718. Min Act: -0.0000

Data Index: 272357 (The Pile)

Max Activating Token Index: 193