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

Dataset: The Pile

Neuron 3551 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: 1.2429. Min Range: -1.2429

Max Act: 1.2429. Min Act: -0.0000

Data Index: 1813989 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.1703. Min Act: -0.0000

Data Index: 1167491 (The Pile)

Max Activating Token Index: 525

Text #2

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.0801. Min Act: -0.0000

Data Index: 1184503 (The Pile)

Max Activating Token Index: 751

Text #3

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.0301. Min Act: -0.0000

Data Index: 1097145 (The Pile)

Max Activating Token Index: 517

Text #4

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.0508. Min Act: -0.0000

Data Index: 878806 (The Pile)

Max Activating Token Index: 33

Text #5

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.0189. Min Act: -0.0000

Data Index: 297074 (The Pile)

Max Activating Token Index: 744

Text #6

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.0496. Min Act: -0.0000

Data Index: 1814134 (The Pile)

Max Activating Token Index: 503

Text #7

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.0508. Min Act: -0.0000

Data Index: 1898462 (The Pile)

Max Activating Token Index: 347

Text #8

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.0999. Min Act: -0.0000

Data Index: 1420606 (The Pile)

Max Activating Token Index: 557

Text #9

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.9842. Min Act: -0.0000

Data Index: 97827 (The Pile)

Max Activating Token Index: 794

Text #10

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.9287. Min Act: -0.0000

Data Index: 1889707 (The Pile)

Max Activating Token Index: 406

Text #11

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.9408. Min Act: -0.0000

Data Index: 1172728 (The Pile)

Max Activating Token Index: 971

Text #12

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1288012 (The Pile)

Max Activating Token Index: 974

Text #13

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.8948. Min Act: -0.0000

Data Index: 1332846 (The Pile)

Max Activating Token Index: 781

Text #14

Max Range: 1.2429. Min Range: -1.2429

Max Act: 1.0087. Min Act: -0.0000

Data Index: 1615153 (The Pile)

Max Activating Token Index: 322

Text #15

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.9488. Min Act: -0.0000

Data Index: 1427956 (The Pile)

Max Activating Token Index: 51

Text #16

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.9209. Min Act: -0.0000

Data Index: 1958678 (The Pile)

Max Activating Token Index: 222

Text #17

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.8515. Min Act: -0.0000

Data Index: 98144 (The Pile)

Max Activating Token Index: 767

Text #18

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.8789. Min Act: -0.0000

Data Index: 977025 (The Pile)

Max Activating Token Index: 644

Text #19

Max Range: 1.2429. Min Range: -1.2429

Max Act: 0.8756. Min Act: -0.0000

Data Index: 1000443 (The Pile)

Max Activating Token Index: 118