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

Dataset: The Pile

Neuron 618 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.6527. Min Act: -0.0000

Data Index: 1710197 (The Pile)

Max Activating Token Index: 324

Text #1

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.5947. Min Act: -0.0000

Data Index: 388480 (The Pile)

Max Activating Token Index: 129

Text #2

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.5256. Min Act: -0.0000

Data Index: 1579553 (The Pile)

Max Activating Token Index: 127

Text #3

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.5999. Min Act: -0.0000

Data Index: 1840672 (The Pile)

Max Activating Token Index: 182

Text #4

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.6645. Min Act: -0.0000

Data Index: 262423 (The Pile)

Max Activating Token Index: 370

Text #5

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.5593. Min Act: -0.0000

Data Index: 1373887 (The Pile)

Max Activating Token Index: 499

Text #6

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.5496. Min Act: -0.0001

Data Index: 880824 (The Pile)

Max Activating Token Index: 366

Text #7

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.5185. Min Act: -0.0000

Data Index: 389278 (The Pile)

Max Activating Token Index: 233

Text #8

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.3510. Min Act: -0.0000

Data Index: 348797 (The Pile)

Max Activating Token Index: 52

Text #9

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.5435. Min Act: -0.0000

Data Index: 799068 (The Pile)

Max Activating Token Index: 117

Text #10

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.3292. Min Act: -0.0000

Data Index: 1769785 (The Pile)

Max Activating Token Index: 688

Text #11

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.3878. Min Act: -0.0000

Data Index: 412913 (The Pile)

Max Activating Token Index: 841

Text #12

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.4034. Min Act: -0.0000

Data Index: 6494 (The Pile)

Max Activating Token Index: 825

Text #13

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.4116. Min Act: -0.0001

Data Index: 1160416 (The Pile)

Max Activating Token Index: 327

Text #14

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.4101. Min Act: -0.0000

Data Index: 1675016 (The Pile)

Max Activating Token Index: 491

Text #15

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.4055. Min Act: -0.0000

Data Index: 1691106 (The Pile)

Max Activating Token Index: 35

Text #16

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.1020. Min Act: -0.0000

Data Index: 644675 (The Pile)

Max Activating Token Index: 863

Text #17

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.2636. Min Act: -0.0000

Data Index: 790413 (The Pile)

Max Activating Token Index: 118

Text #18

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.2916. Min Act: -0.0000

Data Index: 1104263 (The Pile)

Max Activating Token Index: 101

Text #19

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.2135. Min Act: -0.0000

Data Index: 1876202 (The Pile)

Max Activating Token Index: 628