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

Dataset: The Pile

Neuron 3546 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2481. Min Act: -0.0000

Data Index: 1505131 (The Pile)

Max Activating Token Index: 501

Text #1

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2356. Min Act: -0.0000

Data Index: 1404684 (The Pile)

Max Activating Token Index: 319

Text #2

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1270205 (The Pile)

Max Activating Token Index: 632

Text #3

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2315. Min Act: -0.0000

Data Index: 953251 (The Pile)

Max Activating Token Index: 569

Text #4

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1425832 (The Pile)

Max Activating Token Index: 594

Text #5

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1220957 (The Pile)

Max Activating Token Index: 602

Text #6

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2364. Min Act: -0.0000

Data Index: 232596 (The Pile)

Max Activating Token Index: 605

Text #7

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2328. Min Act: -0.0000

Data Index: 67698 (The Pile)

Max Activating Token Index: 415

Text #8

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1808910 (The Pile)

Max Activating Token Index: 764

Text #9

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1744366 (The Pile)

Max Activating Token Index: 16

Text #10

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1433167 (The Pile)

Max Activating Token Index: 375

Text #11

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2045. Min Act: -0.0000

Data Index: 806082 (The Pile)

Max Activating Token Index: 737

Text #12

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1953. Min Act: -0.0000

Data Index: 627216 (The Pile)

Max Activating Token Index: 808

Text #13

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1903. Min Act: -0.0000

Data Index: 269842 (The Pile)

Max Activating Token Index: 685

Text #14

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2041. Min Act: -0.0000

Data Index: 324269 (The Pile)

Max Activating Token Index: 610

Text #15

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1882257 (The Pile)

Max Activating Token Index: 316

Text #16

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1822. Min Act: -0.0000

Data Index: 1522006 (The Pile)

Max Activating Token Index: 650

Text #17

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2070. Min Act: -0.0000

Data Index: 23741 (The Pile)

Max Activating Token Index: 420

Text #18

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1875772 (The Pile)

Max Activating Token Index: 294

Text #19

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1804. Min Act: -0.0000

Data Index: 1679502 (The Pile)

Max Activating Token Index: 845