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

Dataset: The Pile

Neuron 4785 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6579. Min Act: -0.0000

Data Index: 863797 (The Pile)

Max Activating Token Index: 768

Text #1

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.6799. Min Act: -0.0000

Data Index: 725700 (The Pile)

Max Activating Token Index: 3

Text #2

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5947. Min Act: -0.0000

Data Index: 958167 (The Pile)

Max Activating Token Index: 329

Text #3

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1414939 (The Pile)

Max Activating Token Index: 552

Text #4

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5605. Min Act: -0.0000

Data Index: 1071766 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5758. Min Act: -0.0000

Data Index: 602710 (The Pile)

Max Activating Token Index: 254

Text #6

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5900. Min Act: -0.0000

Data Index: 1079018 (The Pile)

Max Activating Token Index: 152

Text #7

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1911370 (The Pile)

Max Activating Token Index: 471

Text #8

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1471921 (The Pile)

Max Activating Token Index: 358

Text #9

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.4977. Min Act: -0.0000

Data Index: 511849 (The Pile)

Max Activating Token Index: 1005

Text #10

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5095. Min Act: -0.0000

Data Index: 477709 (The Pile)

Max Activating Token Index: 1002

Text #11

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1723046 (The Pile)

Max Activating Token Index: 349

Text #12

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5165. Min Act: -0.0000

Data Index: 1504875 (The Pile)

Max Activating Token Index: 341

Text #13

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5167. Min Act: -0.0000

Data Index: 200407 (The Pile)

Max Activating Token Index: 774

Text #14

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1230136 (The Pile)

Max Activating Token Index: 204

Text #15

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5203. Min Act: -0.0000

Data Index: 13906 (The Pile)

Max Activating Token Index: 491

Text #16

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5109. Min Act: -0.0000

Data Index: 17560 (The Pile)

Max Activating Token Index: 218

Text #17

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.5013. Min Act: -0.0000

Data Index: 1793910 (The Pile)

Max Activating Token Index: 691

Text #18

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.4808. Min Act: -0.0000

Data Index: 448871 (The Pile)

Max Activating Token Index: 181

Text #19

Max Range: 0.6799. Min Range: -0.6799

Max Act: 0.4613. Min Act: -0.0000

Data Index: 685962 (The Pile)

Max Activating Token Index: 3