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

Dataset: The Pile

Neuron 4703 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: 0.8633. Min Range: -0.8633

Max Act: 0.8633. Min Act: -0.0000

Data Index: 13784 (The Pile)

Max Activating Token Index: 767

Text #1

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.8294. Min Act: -0.0000

Data Index: 295003 (The Pile)

Max Activating Token Index: 684

Text #2

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.8494. Min Act: -0.0000

Data Index: 599866 (The Pile)

Max Activating Token Index: 581

Text #3

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.6928. Min Act: -0.0000

Data Index: 357002 (The Pile)

Max Activating Token Index: 592

Text #4

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1747446 (The Pile)

Max Activating Token Index: 405

Text #5

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.6100. Min Act: -0.0000

Data Index: 481659 (The Pile)

Max Activating Token Index: 112

Text #6

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1218275 (The Pile)

Max Activating Token Index: 210

Text #7

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.6118. Min Act: -0.0000

Data Index: 808722 (The Pile)

Max Activating Token Index: 760

Text #8

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.6195. Min Act: -0.0000

Data Index: 1086820 (The Pile)

Max Activating Token Index: 155

Text #9

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.6211. Min Act: -0.0000

Data Index: 594994 (The Pile)

Max Activating Token Index: 397

Text #10

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.6348. Min Act: -0.0000

Data Index: 897157 (The Pile)

Max Activating Token Index: 871

Text #11

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.6358. Min Act: -0.0000

Data Index: 187648 (The Pile)

Max Activating Token Index: 445

Text #12

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.5462. Min Act: -0.0000

Data Index: 944008 (The Pile)

Max Activating Token Index: 827

Text #13

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1636740 (The Pile)

Max Activating Token Index: 40

Text #14

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1421318 (The Pile)

Max Activating Token Index: 986

Text #15

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.5766. Min Act: -0.0000

Data Index: 236074 (The Pile)

Max Activating Token Index: 391

Text #16

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.5814. Min Act: -0.0000

Data Index: 41015 (The Pile)

Max Activating Token Index: 706

Text #17

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.5027. Min Act: 0.0000

Data Index: 279909 (The Pile)

Max Activating Token Index: 672

Text #18

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.5292. Min Act: -0.0000

Data Index: 926517 (The Pile)

Max Activating Token Index: 303

Text #19

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1373493 (The Pile)

Max Activating Token Index: 432