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

Dataset: The Pile

Neuron 759 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: 1.8677. Min Range: -1.8677

Max Act: 1.8015. Min Act: -0.0000

Data Index: 104214 (The Pile)

Max Activating Token Index: 30

Text #1

Max Range: 1.8677. Min Range: -1.8677

Max Act: 1.8677. Min Act: -0.0000

Data Index: 1867168 (The Pile)

Max Activating Token Index: 394

Text #2

Max Range: 1.8677. Min Range: -1.8677

Max Act: 1.6629. Min Act: -0.0000

Data Index: 1381159 (The Pile)

Max Activating Token Index: 82

Text #3

Max Range: 1.8677. Min Range: -1.8677

Max Act: 1.8342. Min Act: -0.0000

Data Index: 32203 (The Pile)

Max Activating Token Index: 55

Text #4

Max Range: 1.8677. Min Range: -1.8677

Max Act: 1.6891. Min Act: -0.0000

Data Index: 1792839 (The Pile)

Max Activating Token Index: 560

Text #5

Max Range: 1.8677. Min Range: -1.8677

Max Act: 1.6782. Min Act: -0.0000

Data Index: 783723 (The Pile)

Max Activating Token Index: 93

Text #6

Max Range: 1.8677. Min Range: -1.8677

Max Act: 1.5835. Min Act: -0.0000

Data Index: 246930 (The Pile)

Max Activating Token Index: 532

Text #7

Max Range: 1.8677. Min Range: -1.8677

Max Act: 1.4960. Min Act: -0.0000

Data Index: 1387230 (The Pile)

Max Activating Token Index: 676

Text #8

Max Range: 1.8677. Min Range: -1.8677

Max Act: 1.4664. Min Act: -0.0000

Data Index: 971822 (The Pile)

Max Activating Token Index: 674

Text #9

Max Range: 1.8677. Min Range: -1.8677

Max Act: 1.6279. Min Act: -0.0000

Data Index: 1339211 (The Pile)

Max Activating Token Index: 172

Text #10

Max Range: 1.8677. Min Range: -1.8677

Max Act: 1.4537. Min Act: -0.0000

Data Index: 1865885 (The Pile)

Max Activating Token Index: 932

Text #11

Max Range: 1.8677. Min Range: -1.8677

Max Act: 1.2760. Min Act: -0.0000

Data Index: 1605930 (The Pile)

Max Activating Token Index: 904

Text #12

Max Range: 1.8677. Min Range: -1.8677

Max Act: 1.6029. Min Act: -0.0000

Data Index: 1377780 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 1.8677. Min Range: -1.8677

Max Act: 1.3339. Min Act: -0.0000

Data Index: 892454 (The Pile)

Max Activating Token Index: 544

Text #14

Max Range: 1.8677. Min Range: -1.8677

Max Act: 1.2484. Min Act: -0.0000

Data Index: 424869 (The Pile)

Max Activating Token Index: 128

Text #15

Max Range: 1.8677. Min Range: -1.8677

Max Act: 1.5753. Min Act: -0.0000

Data Index: 590544 (The Pile)

Max Activating Token Index: 848

Text #16

Max Range: 1.8677. Min Range: -1.8677

Max Act: 1.4772. Min Act: -0.0000

Data Index: 1553139 (The Pile)

Max Activating Token Index: 466

Text #17

Max Range: 1.8677. Min Range: -1.8677

Max Act: 1.5550. Min Act: -0.0000

Data Index: 149103 (The Pile)

Max Activating Token Index: 25

Text #18

Max Range: 1.8677. Min Range: -1.8677

Max Act: 1.3144. Min Act: -0.0000

Data Index: 460268 (The Pile)

Max Activating Token Index: 805

Text #19

Max Range: 1.8677. Min Range: -1.8677

Max Act: 1.4605. Min Act: -0.0000

Data Index: 1991208 (The Pile)

Max Activating Token Index: 598