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

Dataset: The Pile

Neuron 4205 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: 1.6710. Min Range: -1.6710

Max Act: 1.6710. Min Act: -0.0000

Data Index: 1915611 (The Pile)

Max Activating Token Index: 933

Text #1

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.5651. Min Act: -0.0000

Data Index: 1962127 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.5307. Min Act: 0.0000

Data Index: 745221 (The Pile)

Max Activating Token Index: 697

Text #3

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.5260. Min Act: -0.0000

Data Index: 1322914 (The Pile)

Max Activating Token Index: 352

Text #4

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.5280. Min Act: -0.0000

Data Index: 533653 (The Pile)

Max Activating Token Index: 772

Text #5

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.4802. Min Act: -0.0000

Data Index: 1588873 (The Pile)

Max Activating Token Index: 121

Text #6

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.4587. Min Act: -0.0000

Data Index: 14777 (The Pile)

Max Activating Token Index: 308

Text #7

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.4553. Min Act: -0.0000

Data Index: 882617 (The Pile)

Max Activating Token Index: 549

Text #8

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.4361. Min Act: -0.0000

Data Index: 1811098 (The Pile)

Max Activating Token Index: 450

Text #9

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.5068. Min Act: -0.0000

Data Index: 693534 (The Pile)

Max Activating Token Index: 979

Text #10

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.4970. Min Act: -0.0000

Data Index: 1018362 (The Pile)

Max Activating Token Index: 667

Text #11

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.4263. Min Act: -0.0000

Data Index: 643816 (The Pile)

Max Activating Token Index: 612

Text #12

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.3362. Min Act: -0.0000

Data Index: 1369959 (The Pile)

Max Activating Token Index: 275

Text #13

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.3953. Min Act: -0.0000

Data Index: 721176 (The Pile)

Max Activating Token Index: 72

Text #14

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.3902. Min Act: -0.0000

Data Index: 973943 (The Pile)

Max Activating Token Index: 83

Text #15

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.3159. Min Act: -0.0000

Data Index: 1357468 (The Pile)

Max Activating Token Index: 853

Text #16

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.3754. Min Act: -0.0000

Data Index: 761010 (The Pile)

Max Activating Token Index: 51

Text #17

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.3156. Min Act: -0.0000

Data Index: 691673 (The Pile)

Max Activating Token Index: 122

Text #18

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.3718. Min Act: -0.0000

Data Index: 869863 (The Pile)

Max Activating Token Index: 473

Text #19

Max Range: 1.6710. Min Range: -1.6710

Max Act: 1.2914. Min Act: -0.0000

Data Index: 239550 (The Pile)

Max Activating Token Index: 136