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

Dataset: The Pile

Neuron 3785 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.6415. Min Act: -0.0000

Data Index: 1768412 (The Pile)

Max Activating Token Index: 303

Text #1

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.2647. Min Act: -0.0000

Data Index: 819533 (The Pile)

Max Activating Token Index: 655

Text #2

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.4281. Min Act: -0.0000

Data Index: 1937336 (The Pile)

Max Activating Token Index: 481

Text #3

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.5432. Min Act: -0.0000

Data Index: 1469014 (The Pile)

Max Activating Token Index: 501

Text #4

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.3433. Min Act: -0.0000

Data Index: 1574502 (The Pile)

Max Activating Token Index: 872

Text #5

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.3763. Min Act: -0.0000

Data Index: 882952 (The Pile)

Max Activating Token Index: 369

Text #6

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.3844. Min Act: -0.0000

Data Index: 179768 (The Pile)

Max Activating Token Index: 758

Text #7

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.2773. Min Act: -0.0000

Data Index: 354922 (The Pile)

Max Activating Token Index: 511

Text #8

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.3350. Min Act: -0.0000

Data Index: 1371855 (The Pile)

Max Activating Token Index: 500

Text #9

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.3010. Min Act: -0.0000

Data Index: 1384461 (The Pile)

Max Activating Token Index: 841

Text #10

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.2363. Min Act: -0.0000

Data Index: 324994 (The Pile)

Max Activating Token Index: 180

Text #11

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1222998 (The Pile)

Max Activating Token Index: 183

Text #12

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.2372. Min Act: -0.0000

Data Index: 145366 (The Pile)

Max Activating Token Index: 36

Text #13

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.2394. Min Act: -0.0000

Data Index: 485989 (The Pile)

Max Activating Token Index: 344

Text #14

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.2121. Min Act: -0.0000

Data Index: 1387242 (The Pile)

Max Activating Token Index: 87

Text #15

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.1536. Min Act: -0.0000

Data Index: 1711569 (The Pile)

Max Activating Token Index: 573

Text #16

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.2174. Min Act: -0.0000

Data Index: 1781159 (The Pile)

Max Activating Token Index: 117

Text #17

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.2555. Min Act: -0.0000

Data Index: 345655 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.1961. Min Act: -0.0000

Data Index: 413287 (The Pile)

Max Activating Token Index: 397

Text #19

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.0938. Min Act: -0.0000

Data Index: 833008 (The Pile)

Max Activating Token Index: 907