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

Dataset: The Pile

Neuron 654 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.3761. Min Act: -0.0000

Data Index: 1217286 (The Pile)

Max Activating Token Index: 897

Text #1

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.3087. Min Act: -0.0000

Data Index: 128504 (The Pile)

Max Activating Token Index: 165

Text #2

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.3035. Min Act: -0.0000

Data Index: 1331791 (The Pile)

Max Activating Token Index: 693

Text #3

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.1538. Min Act: -0.0000

Data Index: 1818885 (The Pile)

Max Activating Token Index: 699

Text #4

Max Range: 1.3761. Min Range: -1.3761

Max Act: 1.0562. Min Act: -0.0000

Data Index: 1296106 (The Pile)

Max Activating Token Index: 163

Text #5

Max Range: 1.3761. Min Range: -1.3761

Max Act: 0.9717. Min Act: -0.0000

Data Index: 132098 (The Pile)

Max Activating Token Index: 116

Text #6

Max Range: 1.3761. Min Range: -1.3761

Max Act: 0.9091. Min Act: -0.0000

Data Index: 507673 (The Pile)

Max Activating Token Index: 712

Text #7

Max Range: 1.3761. Min Range: -1.3761

Max Act: 0.9749. Min Act: -0.0000

Data Index: 105834 (The Pile)

Max Activating Token Index: 548

Text #8

Max Range: 1.3761. Min Range: -1.3761

Max Act: 0.9112. Min Act: -0.0000

Data Index: 1599219 (The Pile)

Max Activating Token Index: 411

Text #9

Max Range: 1.3761. Min Range: -1.3761

Max Act: 0.8878. Min Act: -0.0000

Data Index: 380511 (The Pile)

Max Activating Token Index: 962

Text #10

Max Range: 1.3761. Min Range: -1.3761

Max Act: 0.8140. Min Act: -0.0000

Data Index: 591148 (The Pile)

Max Activating Token Index: 772

Text #11

Max Range: 1.3761. Min Range: -1.3761

Max Act: 0.8524. Min Act: -0.0000

Data Index: 1299596 (The Pile)

Max Activating Token Index: 631

Text #12

Max Range: 1.3761. Min Range: -1.3761

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1196035 (The Pile)

Max Activating Token Index: 614

Text #13

Max Range: 1.3761. Min Range: -1.3761

Max Act: 0.8738. Min Act: 0.0000

Data Index: 227216 (The Pile)

Max Activating Token Index: 1017

Text #14

Max Range: 1.3761. Min Range: -1.3761

Max Act: 0.7932. Min Act: -0.0000

Data Index: 1437979 (The Pile)

Max Activating Token Index: 1017

Text #15

Max Range: 1.3761. Min Range: -1.3761

Max Act: 0.7442. Min Act: -0.0000

Data Index: 1374409 (The Pile)

Max Activating Token Index: 245

Text #16

Max Range: 1.3761. Min Range: -1.3761

Max Act: 0.7379. Min Act: -0.0000

Data Index: 178564 (The Pile)

Max Activating Token Index: 289

Text #17

Max Range: 1.3761. Min Range: -1.3761

Max Act: 0.7409. Min Act: -0.0000

Data Index: 1766213 (The Pile)

Max Activating Token Index: 1002

Text #18

Max Range: 1.3761. Min Range: -1.3761

Max Act: 0.7274. Min Act: -0.0000

Data Index: 1179842 (The Pile)

Max Activating Token Index: 952

Text #19

Max Range: 1.3761. Min Range: -1.3761

Max Act: 0.7679. Min Act: -0.0000

Data Index: 1549525 (The Pile)

Max Activating Token Index: 264