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

Dataset: The Pile

Neuron 4015 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.8320. Min Act: -0.0000

Data Index: 277420 (The Pile)

Max Activating Token Index: 654

Text #1

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.8521. Min Act: -0.0000

Data Index: 58447 (The Pile)

Max Activating Token Index: 723

Text #2

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7284. Min Act: -0.0000

Data Index: 1165130 (The Pile)

Max Activating Token Index: 464

Text #3

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7093. Min Act: -0.0000

Data Index: 464848 (The Pile)

Max Activating Token Index: 535

Text #4

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6532. Min Act: -0.0000

Data Index: 859548 (The Pile)

Max Activating Token Index: 821

Text #5

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6917. Min Act: -0.0000

Data Index: 1678909 (The Pile)

Max Activating Token Index: 963

Text #6

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6599. Min Act: 0.0003

Data Index: 1282824 (The Pile)

Max Activating Token Index: 354

Text #7

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1499814 (The Pile)

Max Activating Token Index: 702

Text #8

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7220. Min Act: -0.0000

Data Index: 1993880 (The Pile)

Max Activating Token Index: 450

Text #9

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1176071 (The Pile)

Max Activating Token Index: 887

Text #10

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6013. Min Act: -0.0000

Data Index: 312913 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7237. Min Act: -0.0000

Data Index: 697977 (The Pile)

Max Activating Token Index: 767

Text #12

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6031. Min Act: -0.0000

Data Index: 510586 (The Pile)

Max Activating Token Index: 625

Text #13

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6395. Min Act: -0.0000

Data Index: 967733 (The Pile)

Max Activating Token Index: 314

Text #14

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6251. Min Act: 0.0000

Data Index: 1799170 (The Pile)

Max Activating Token Index: 383

Text #15

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6559. Min Act: -0.0000

Data Index: 428503 (The Pile)

Max Activating Token Index: 289

Text #16

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1296622 (The Pile)

Max Activating Token Index: 1005

Text #17

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6112. Min Act: -0.0000

Data Index: 835784 (The Pile)

Max Activating Token Index: 870

Text #18

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.5956. Min Act: -0.0000

Data Index: 380169 (The Pile)

Max Activating Token Index: 887

Text #19

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.5970. Min Act: -0.0000

Data Index: 1249461 (The Pile)

Max Activating Token Index: 140