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

Dataset: The Pile

Neuron 4606 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: 0.7332. Min Range: -0.7332

Max Act: 0.7332. Min Act: -0.0000

Data Index: 1125181 (The Pile)

Max Activating Token Index: 805

Text #1

Max Range: 0.7332. Min Range: -0.7332

Max Act: 0.6211. Min Act: -0.0000

Data Index: 337805 (The Pile)

Max Activating Token Index: 797

Text #2

Max Range: 0.7332. Min Range: -0.7332

Max Act: 0.5947. Min Act: -0.0000

Data Index: 582740 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 0.7332. Min Range: -0.7332

Max Act: 0.5962. Min Act: -0.0000

Data Index: 1819107 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 0.7332. Min Range: -0.7332

Max Act: 0.5829. Min Act: -0.0000

Data Index: 1919420 (The Pile)

Max Activating Token Index: 603

Text #5

Max Range: 0.7332. Min Range: -0.7332

Max Act: 0.5987. Min Act: -0.0000

Data Index: 263772 (The Pile)

Max Activating Token Index: 797

Text #6

Max Range: 0.7332. Min Range: -0.7332

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1595331 (The Pile)

Max Activating Token Index: 784

Text #7

Max Range: 0.7332. Min Range: -0.7332

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1175314 (The Pile)

Max Activating Token Index: 939

Text #8

Max Range: 0.7332. Min Range: -0.7332

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1102832 (The Pile)

Max Activating Token Index: 927

Text #9

Max Range: 0.7332. Min Range: -0.7332

Max Act: 0.5638. Min Act: -0.0000

Data Index: 920713 (The Pile)

Max Activating Token Index: 415

Text #10

Max Range: 0.7332. Min Range: -0.7332

Max Act: 0.5464. Min Act: -0.0000

Data Index: 342453 (The Pile)

Max Activating Token Index: 688

Text #11

Max Range: 0.7332. Min Range: -0.7332

Max Act: 0.5423. Min Act: -0.0000

Data Index: 534191 (The Pile)

Max Activating Token Index: 811

Text #12

Max Range: 0.7332. Min Range: -0.7332

Max Act: 0.5988. Min Act: -0.0000

Data Index: 158013 (The Pile)

Max Activating Token Index: 443

Text #13

Max Range: 0.7332. Min Range: -0.7332

Max Act: 0.5431. Min Act: -0.0000

Data Index: 194975 (The Pile)

Max Activating Token Index: 955

Text #14

Max Range: 0.7332. Min Range: -0.7332

Max Act: 0.5580. Min Act: -0.0000

Data Index: 1970371 (The Pile)

Max Activating Token Index: 881

Text #15

Max Range: 0.7332. Min Range: -0.7332

Max Act: 0.5442. Min Act: -0.0000

Data Index: 1680630 (The Pile)

Max Activating Token Index: 627

Text #16

Max Range: 0.7332. Min Range: -0.7332

Max Act: 0.4858. Min Act: -0.0000

Data Index: 1799451 (The Pile)

Max Activating Token Index: 1013

Text #17

Max Range: 0.7332. Min Range: -0.7332

Max Act: 0.5569. Min Act: -0.0000

Data Index: 634383 (The Pile)

Max Activating Token Index: 681

Text #18

Max Range: 0.7332. Min Range: -0.7332

Max Act: 0.4965. Min Act: -0.0000

Data Index: 194577 (The Pile)

Max Activating Token Index: 968

Text #19

Max Range: 0.7332. Min Range: -0.7332

Max Act: 0.5391. Min Act: -0.0000

Data Index: 561831 (The Pile)

Max Activating Token Index: 1001