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

Dataset: The Pile

Neuron 2441 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: 0.8677. Min Range: -0.8677

Max Act: 0.8677. Min Act: -0.0000

Data Index: 123635 (The Pile)

Max Activating Token Index: 146

Text #1

Max Range: 0.8677. Min Range: -0.8677

Max Act: 0.8276. Min Act: -0.0000

Data Index: 369161 (The Pile)

Max Activating Token Index: 423

Text #2

Max Range: 0.8677. Min Range: -0.8677

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1844707 (The Pile)

Max Activating Token Index: 522

Text #3

Max Range: 0.8677. Min Range: -0.8677

Max Act: 0.7940. Min Act: -0.0000

Data Index: 1811851 (The Pile)

Max Activating Token Index: 979

Text #4

Max Range: 0.8677. Min Range: -0.8677

Max Act: 0.7586. Min Act: -0.0000

Data Index: 182703 (The Pile)

Max Activating Token Index: 722

Text #5

Max Range: 0.8677. Min Range: -0.8677

Max Act: 0.7050. Min Act: -0.0000

Data Index: 1940294 (The Pile)

Max Activating Token Index: 768

Text #6

Max Range: 0.8677. Min Range: -0.8677

Max Act: 0.7184. Min Act: -0.0000

Data Index: 1262471 (The Pile)

Max Activating Token Index: 674

Text #7

Max Range: 0.8677. Min Range: -0.8677

Max Act: 0.7464. Min Act: -0.0000

Data Index: 1560844 (The Pile)

Max Activating Token Index: 873

Text #8

Max Range: 0.8677. Min Range: -0.8677

Max Act: 0.6390. Min Act: -0.0000

Data Index: 784550 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 0.8677. Min Range: -0.8677

Max Act: 0.6941. Min Act: -0.0000

Data Index: 397092 (The Pile)

Max Activating Token Index: 280

Text #10

Max Range: 0.8677. Min Range: -0.8677

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1546435 (The Pile)

Max Activating Token Index: 453

Text #11

Max Range: 0.8677. Min Range: -0.8677

Max Act: 0.6450. Min Act: -0.0000

Data Index: 1128904 (The Pile)

Max Activating Token Index: 162

Text #12

Max Range: 0.8677. Min Range: -0.8677

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1380335 (The Pile)

Max Activating Token Index: 934

Text #13

Max Range: 0.8677. Min Range: -0.8677

Max Act: 0.6532. Min Act: -0.0000

Data Index: 226963 (The Pile)

Max Activating Token Index: 233

Text #14

Max Range: 0.8677. Min Range: -0.8677

Max Act: 0.6107. Min Act: -0.0000

Data Index: 1181871 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 0.8677. Min Range: -0.8677

Max Act: 0.6934. Min Act: -0.0000

Data Index: 1843727 (The Pile)

Max Activating Token Index: 900

Text #16

Max Range: 0.8677. Min Range: -0.8677

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1353613 (The Pile)

Max Activating Token Index: 470

Text #17

Max Range: 0.8677. Min Range: -0.8677

Max Act: 0.6227. Min Act: -0.0000

Data Index: 861683 (The Pile)

Max Activating Token Index: 679

Text #18

Max Range: 0.8677. Min Range: -0.8677

Max Act: 0.6276. Min Act: -0.0000

Data Index: 1167519 (The Pile)

Max Activating Token Index: 385

Text #19

Max Range: 0.8677. Min Range: -0.8677

Max Act: 0.6489. Min Act: -0.0000

Data Index: 179049 (The Pile)

Max Activating Token Index: 17