Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3419 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.7012. Min Act: -0.0000

Data Index: 1659703 (The Pile)

Max Activating Token Index: 947

Text #1

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1862599 (The Pile)

Max Activating Token Index: 77

Text #2

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.6029. Min Act: -0.0000

Data Index: 502258 (The Pile)

Max Activating Token Index: 360

Text #3

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1498813 (The Pile)

Max Activating Token Index: 575

Text #4

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1211391 (The Pile)

Max Activating Token Index: 209

Text #5

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5139. Min Act: -0.0000

Data Index: 1564430 (The Pile)

Max Activating Token Index: 1020

Text #6

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1101863 (The Pile)

Max Activating Token Index: 144

Text #7

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5130. Min Act: -0.0000

Data Index: 461243 (The Pile)

Max Activating Token Index: 519

Text #8

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4904. Min Act: -0.0000

Data Index: 1765364 (The Pile)

Max Activating Token Index: 90

Text #9

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4897. Min Act: -0.0000

Data Index: 723160 (The Pile)

Max Activating Token Index: 385

Text #10

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5139. Min Act: -0.0000

Data Index: 1776908 (The Pile)

Max Activating Token Index: 799

Text #11

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5177. Min Act: -0.0000

Data Index: 836240 (The Pile)

Max Activating Token Index: 539

Text #12

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4826. Min Act: -0.0000

Data Index: 217382 (The Pile)

Max Activating Token Index: 65

Text #13

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5116. Min Act: -0.0000

Data Index: 1562142 (The Pile)

Max Activating Token Index: 121

Text #14

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4517. Min Act: -0.0000

Data Index: 1508829 (The Pile)

Max Activating Token Index: 58

Text #15

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4925. Min Act: -0.0000

Data Index: 957053 (The Pile)

Max Activating Token Index: 224

Text #16

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4785. Min Act: -0.0000

Data Index: 3404 (The Pile)

Max Activating Token Index: 878

Text #17

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1820683 (The Pile)

Max Activating Token Index: 742

Text #18

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1081110 (The Pile)

Max Activating Token Index: 70

Text #19

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4657. Min Act: -0.0000

Data Index: 109817 (The Pile)

Max Activating Token Index: 170