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

Dataset: The Pile

Neuron 2791 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: 1.3517. Min Range: -1.3517

Max Act: 1.3517. Min Act: -0.0000

Data Index: 1105682 (The Pile)

Max Activating Token Index: 1022

Text #1

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.3100. Min Act: -0.0000

Data Index: 348705 (The Pile)

Max Activating Token Index: 599

Text #2

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.3259. Min Act: -0.0000

Data Index: 438045 (The Pile)

Max Activating Token Index: 418

Text #3

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.3312. Min Act: -0.0000

Data Index: 96695 (The Pile)

Max Activating Token Index: 679

Text #4

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.2829. Min Act: -0.0000

Data Index: 78077 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1642864 (The Pile)

Max Activating Token Index: 868

Text #6

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1717010 (The Pile)

Max Activating Token Index: 387

Text #7

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1661653 (The Pile)

Max Activating Token Index: 375

Text #8

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.2605. Min Act: -0.0000

Data Index: 1781524 (The Pile)

Max Activating Token Index: 818

Text #9

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.2695. Min Act: -0.0000

Data Index: 597216 (The Pile)

Max Activating Token Index: 990

Text #10

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.2773. Min Act: -0.0000

Data Index: 1988803 (The Pile)

Max Activating Token Index: 754

Text #11

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1798324 (The Pile)

Max Activating Token Index: 328

Text #12

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.2613. Min Act: -0.0000

Data Index: 863889 (The Pile)

Max Activating Token Index: 246

Text #13

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.2189. Min Act: -0.0000

Data Index: 1627678 (The Pile)

Max Activating Token Index: 951

Text #14

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.2614. Min Act: -0.0000

Data Index: 513932 (The Pile)

Max Activating Token Index: 866

Text #15

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.2461. Min Act: -0.0000

Data Index: 1378898 (The Pile)

Max Activating Token Index: 425

Text #16

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1107598 (The Pile)

Max Activating Token Index: 1004

Text #17

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.2264. Min Act: -0.0000

Data Index: 681424 (The Pile)

Max Activating Token Index: 997

Text #18

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.2476. Min Act: -0.0000

Data Index: 987794 (The Pile)

Max Activating Token Index: 417

Text #19

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1016924 (The Pile)

Max Activating Token Index: 293