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

Dataset: The Pile

Neuron 381 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: 3.9129. Min Range: -3.9129

Max Act: 3.6430. Min Act: -0.0000

Data Index: 950019 (The Pile)

Max Activating Token Index: 907

Text #1

Max Range: 3.9129. Min Range: -3.9129

Max Act: 3.9074. Min Act: -0.0000

Data Index: 244968 (The Pile)

Max Activating Token Index: 954

Text #2

Max Range: 3.9129. Min Range: -3.9129

Max Act: 3.5891. Min Act: -0.0000

Data Index: 1633838 (The Pile)

Max Activating Token Index: 961

Text #3

Max Range: 3.9129. Min Range: -3.9129

Max Act: 3.7348. Min Act: -0.0000

Data Index: 1177177 (The Pile)

Max Activating Token Index: 680

Text #4

Max Range: 3.9129. Min Range: -3.9129

Max Act: 3.9129. Min Act: -0.0000

Data Index: 1606791 (The Pile)

Max Activating Token Index: 766

Text #5

Max Range: 3.9129. Min Range: -3.9129

Max Act: 3.7059. Min Act: -0.0000

Data Index: 791671 (The Pile)

Max Activating Token Index: 648

Text #6

Max Range: 3.9129. Min Range: -3.9129

Max Act: 3.6199. Min Act: -0.0000

Data Index: 1902884 (The Pile)

Max Activating Token Index: 146

Text #7

Max Range: 3.9129. Min Range: -3.9129

Max Act: 3.5947. Min Act: -0.0000

Data Index: 254546 (The Pile)

Max Activating Token Index: 130

Text #8

Max Range: 3.9129. Min Range: -3.9129

Max Act: 3.4521. Min Act: -0.0000

Data Index: 1350873 (The Pile)

Max Activating Token Index: 239

Text #9

Max Range: 3.9129. Min Range: -3.9129

Max Act: 3.3753. Min Act: -0.0000

Data Index: 430467 (The Pile)

Max Activating Token Index: 1008

Text #10

Max Range: 3.9129. Min Range: -3.9129

Max Act: 3.5236. Min Act: -0.0000

Data Index: 263063 (The Pile)

Max Activating Token Index: 79

Text #11

Max Range: 3.9129. Min Range: -3.9129

Max Act: 3.3720. Min Act: -0.0000

Data Index: 758174 (The Pile)

Max Activating Token Index: 193

Text #12

Max Range: 3.9129. Min Range: -3.9129

Max Act: 3.4833. Min Act: -0.0000

Data Index: 502857 (The Pile)

Max Activating Token Index: 859

Text #13

Max Range: 3.9129. Min Range: -3.9129

Max Act: 3.4848. Min Act: -0.0000

Data Index: 770738 (The Pile)

Max Activating Token Index: 351

Text #14

Max Range: 3.9129. Min Range: -3.9129

Max Act: 3.4501. Min Act: -0.0000

Data Index: 1490465 (The Pile)

Max Activating Token Index: 390

Text #15

Max Range: 3.9129. Min Range: -3.9129

Max Act: 3.4586. Min Act: -0.0000

Data Index: 1292660 (The Pile)

Max Activating Token Index: 313

Text #16

Max Range: 3.9129. Min Range: -3.9129

Max Act: 3.4433. Min Act: -0.0000

Data Index: 1810198 (The Pile)

Max Activating Token Index: 483

Text #17

Max Range: 3.9129. Min Range: -3.9129

Max Act: 3.6009. Min Act: -0.0000

Data Index: 1472160 (The Pile)

Max Activating Token Index: 552

Text #18

Max Range: 3.9129. Min Range: -3.9129

Max Act: 3.6013. Min Act: -0.0000

Data Index: 98255 (The Pile)

Max Activating Token Index: 86

Text #19

Max Range: 3.9129. Min Range: -3.9129

Max Act: 3.6108. Min Act: -0.0000

Data Index: 167606 (The Pile)

Max Activating Token Index: 993