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

Dataset: The Pile

Neuron 3039 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: 0.6130. Min Range: -0.6130

Max Act: 0.6072. Min Act: -0.0000

Data Index: 247522 (The Pile)

Max Activating Token Index: 644

Text #1

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.6130. Min Act: -0.0000

Data Index: 580313 (The Pile)

Max Activating Token Index: 662

Text #2

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1351528 (The Pile)

Max Activating Token Index: 610

Text #3

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5635. Min Act: -0.0000

Data Index: 300633 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5650. Min Act: -0.0000

Data Index: 1116053 (The Pile)

Max Activating Token Index: 542

Text #5

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5918. Min Act: -0.0000

Data Index: 1542818 (The Pile)

Max Activating Token Index: 655

Text #6

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5417. Min Act: -0.0000

Data Index: 1597132 (The Pile)

Max Activating Token Index: 53

Text #7

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1420261 (The Pile)

Max Activating Token Index: 1013

Text #8

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1676346 (The Pile)

Max Activating Token Index: 405

Text #9

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5469. Min Act: -0.0000

Data Index: 441621 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1321406 (The Pile)

Max Activating Token Index: 920

Text #11

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5416. Min Act: -0.0000

Data Index: 789714 (The Pile)

Max Activating Token Index: 947

Text #12

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5214. Min Act: -0.0000

Data Index: 724209 (The Pile)

Max Activating Token Index: 785

Text #13

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5296. Min Act: -0.0000

Data Index: 1026495 (The Pile)

Max Activating Token Index: 860

Text #14

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1396595 (The Pile)

Max Activating Token Index: 192

Text #15

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.4978. Min Act: -0.0000

Data Index: 437620 (The Pile)

Max Activating Token Index: 613

Text #16

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5278. Min Act: -0.0000

Data Index: 512556 (The Pile)

Max Activating Token Index: 883

Text #17

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5103. Min Act: -0.0000

Data Index: 14228 (The Pile)

Max Activating Token Index: 351

Text #18

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5235. Min Act: -0.0000

Data Index: 932893 (The Pile)

Max Activating Token Index: 556

Text #19

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.4873. Min Act: -0.0000

Data Index: 863078 (The Pile)

Max Activating Token Index: 414