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

Dataset: The Pile

Neuron 383 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.9700. Min Act: -0.0000

Data Index: 497390 (The Pile)

Max Activating Token Index: 677

Text #1

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.6545. Min Act: -0.0000

Data Index: 196008 (The Pile)

Max Activating Token Index: 322

Text #2

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.5895. Min Act: -0.0000

Data Index: 1071487 (The Pile)

Max Activating Token Index: 258

Text #3

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.4298. Min Act: -0.0000

Data Index: 669628 (The Pile)

Max Activating Token Index: 39

Text #4

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.5276. Min Act: -0.0000

Data Index: 1073857 (The Pile)

Max Activating Token Index: 752

Text #5

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.4680. Min Act: -0.0000

Data Index: 1059608 (The Pile)

Max Activating Token Index: 445

Text #6

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.3015. Min Act: -0.0000

Data Index: 821531 (The Pile)

Max Activating Token Index: 935

Text #7

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.3193. Min Act: -0.0000

Data Index: 1250785 (The Pile)

Max Activating Token Index: 545

Text #8

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.2863. Min Act: -0.0000

Data Index: 1987419 (The Pile)

Max Activating Token Index: 495

Text #9

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.1796. Min Act: -0.0000

Data Index: 1352995 (The Pile)

Max Activating Token Index: 431

Text #10

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.1977. Min Act: -0.0000

Data Index: 614060 (The Pile)

Max Activating Token Index: 971

Text #11

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.1314. Min Act: -0.0000

Data Index: 1919920 (The Pile)

Max Activating Token Index: 408

Text #12

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.2745. Min Act: -0.0000

Data Index: 827478 (The Pile)

Max Activating Token Index: 216

Text #13

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.2289. Min Act: -0.0000

Data Index: 458974 (The Pile)

Max Activating Token Index: 590

Text #14

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.2180. Min Act: -0.0000

Data Index: 1337221 (The Pile)

Max Activating Token Index: 587

Text #15

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.2182. Min Act: -0.0000

Data Index: 212077 (The Pile)

Max Activating Token Index: 876

Text #16

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.1887. Min Act: -0.0000

Data Index: 530858 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.1687. Min Act: -0.0000

Data Index: 1739502 (The Pile)

Max Activating Token Index: 662

Text #18

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.1777. Min Act: -0.0000

Data Index: 547295 (The Pile)

Max Activating Token Index: 328

Text #19

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.1343. Min Act: -0.0000

Data Index: 635651 (The Pile)

Max Activating Token Index: 184