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

Dataset: The Pile

Neuron 769 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2289. Min Act: -0.0000

Data Index: 1770589 (The Pile)

Max Activating Token Index: 929

Text #1

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2828. Min Act: -0.0000

Data Index: 517034 (The Pile)

Max Activating Token Index: 443

Text #2

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2966. Min Act: -0.0000

Data Index: 417598 (The Pile)

Max Activating Token Index: 933

Text #3

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2789. Min Act: -0.0000

Data Index: 186986 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2632. Min Act: -0.0000

Data Index: 561183 (The Pile)

Max Activating Token Index: 526

Text #5

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2574. Min Act: -0.0000

Data Index: 688417 (The Pile)

Max Activating Token Index: 718

Text #6

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2489. Min Act: -0.0000

Data Index: 611344 (The Pile)

Max Activating Token Index: 944

Text #7

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1123677 (The Pile)

Max Activating Token Index: 775

Text #8

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2486. Min Act: -0.0000

Data Index: 1806585 (The Pile)

Max Activating Token Index: 702

Text #9

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1544213 (The Pile)

Max Activating Token Index: 522

Text #10

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2602. Min Act: -0.0000

Data Index: 3191 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2615. Min Act: -0.0000

Data Index: 37569 (The Pile)

Max Activating Token Index: 902

Text #12

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2192. Min Act: -0.0000

Data Index: 449338 (The Pile)

Max Activating Token Index: 872

Text #13

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1288296 (The Pile)

Max Activating Token Index: 594

Text #14

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2380. Min Act: -0.0000

Data Index: 233013 (The Pile)

Max Activating Token Index: 809

Text #15

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2270. Min Act: -0.0000

Data Index: 519096 (The Pile)

Max Activating Token Index: 805

Text #16

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2432. Min Act: -0.0000

Data Index: 245422 (The Pile)

Max Activating Token Index: 995

Text #17

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2311. Min Act: -0.0000

Data Index: 128347 (The Pile)

Max Activating Token Index: 257

Text #18

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2262. Min Act: -0.0000

Data Index: 221958 (The Pile)

Max Activating Token Index: 449

Text #19

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1429508 (The Pile)

Max Activating Token Index: 834