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

Dataset: The Pile

Neuron 3185 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2255. Min Range: -3.2255

Max Act: 3.1953. Min Act: -0.0000

Data Index: 460343 (The Pile)

Max Activating Token Index: 164

Text #1

Max Range: 3.2255. Min Range: -3.2255

Max Act: 3.2255. Min Act: -0.0000

Data Index: 523040 (The Pile)

Max Activating Token Index: 180

Text #2

Max Range: 3.2255. Min Range: -3.2255

Max Act: 2.9779. Min Act: -0.0000

Data Index: 329093 (The Pile)

Max Activating Token Index: 248

Text #3

Max Range: 3.2255. Min Range: -3.2255

Max Act: 3.0982. Min Act: -0.0000

Data Index: 823166 (The Pile)

Max Activating Token Index: 866

Text #4

Max Range: 3.2255. Min Range: -3.2255

Max Act: 2.7155. Min Act: -0.0000

Data Index: 1022587 (The Pile)

Max Activating Token Index: 891

Text #5

Max Range: 3.2255. Min Range: -3.2255

Max Act: 3.0595. Min Act: -0.0000

Data Index: 1237900 (The Pile)

Max Activating Token Index: 126

Text #6

Max Range: 3.2255. Min Range: -3.2255

Max Act: 2.5782. Min Act: -0.0000

Data Index: 1786351 (The Pile)

Max Activating Token Index: 903

Text #7

Max Range: 3.2255. Min Range: -3.2255

Max Act: 2.7275. Min Act: -0.0000

Data Index: 218385 (The Pile)

Max Activating Token Index: 934

Text #8

Max Range: 3.2255. Min Range: -3.2255

Max Act: 2.7050. Min Act: -0.0000

Data Index: 793961 (The Pile)

Max Activating Token Index: 786

Text #9

Max Range: 3.2255. Min Range: -3.2255

Max Act: 2.6847. Min Act: -0.0000

Data Index: 508644 (The Pile)

Max Activating Token Index: 33

Text #10

Max Range: 3.2255. Min Range: -3.2255

Max Act: 2.5138. Min Act: -0.0000

Data Index: 1949376 (The Pile)

Max Activating Token Index: 762

Text #11

Max Range: 3.2255. Min Range: -3.2255

Max Act: 2.6338. Min Act: -0.0000

Data Index: 1061851 (The Pile)

Max Activating Token Index: 455

Text #12

Max Range: 3.2255. Min Range: -3.2255

Max Act: 2.7473. Min Act: -0.0000

Data Index: 321951 (The Pile)

Max Activating Token Index: 199

Text #13

Max Range: 3.2255. Min Range: -3.2255

Max Act: 2.7714. Min Act: -0.0000

Data Index: 376342 (The Pile)

Max Activating Token Index: 549

Text #14

Max Range: 3.2255. Min Range: -3.2255

Max Act: 2.4084. Min Act: -0.0000

Data Index: 1418741 (The Pile)

Max Activating Token Index: 239

Text #15

Max Range: 3.2255. Min Range: -3.2255

Max Act: 2.5643. Min Act: -0.0000

Data Index: 892850 (The Pile)

Max Activating Token Index: 552

Text #16

Max Range: 3.2255. Min Range: -3.2255

Max Act: 2.5357. Min Act: -0.0000

Data Index: 665070 (The Pile)

Max Activating Token Index: 204

Text #17

Max Range: 3.2255. Min Range: -3.2255

Max Act: 2.3965. Min Act: -0.0000

Data Index: 1511456 (The Pile)

Max Activating Token Index: 675

Text #18

Max Range: 3.2255. Min Range: -3.2255

Max Act: 2.4886. Min Act: -0.0000

Data Index: 78642 (The Pile)

Max Activating Token Index: 744

Text #19

Max Range: 3.2255. Min Range: -3.2255

Max Act: 2.6114. Min Act: -0.0000

Data Index: 505694 (The Pile)

Max Activating Token Index: 150