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

Dataset: The Pile

Neuron 4859 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: 1.9299. Min Range: -1.9299

Max Act: 1.8734. Min Act: -0.0000

Data Index: 1783823 (The Pile)

Max Activating Token Index: 832

Text #1

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.9299. Min Act: -0.0000

Data Index: 1954502 (The Pile)

Max Activating Token Index: 213

Text #2

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.7964. Min Act: -0.0000

Data Index: 732507 (The Pile)

Max Activating Token Index: 479

Text #3

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.7379. Min Act: -0.0000

Data Index: 1166877 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.5582. Min Act: -0.0000

Data Index: 602504 (The Pile)

Max Activating Token Index: 761

Text #5

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.6478. Min Act: -0.0000

Data Index: 1811693 (The Pile)

Max Activating Token Index: 567

Text #6

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.8293. Min Act: -0.0000

Data Index: 1633147 (The Pile)

Max Activating Token Index: 926

Text #7

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.4564. Min Act: -0.0000

Data Index: 1719982 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.6263. Min Act: -0.0000

Data Index: 1813502 (The Pile)

Max Activating Token Index: 566

Text #9

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.6385. Min Act: -0.0000

Data Index: 736542 (The Pile)

Max Activating Token Index: 585

Text #10

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.5287. Min Act: -0.0000

Data Index: 1437905 (The Pile)

Max Activating Token Index: 678

Text #11

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.4706. Min Act: -0.0000

Data Index: 1766128 (The Pile)

Max Activating Token Index: 990

Text #12

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.2883. Min Act: -0.0000

Data Index: 103110 (The Pile)

Max Activating Token Index: 615

Text #13

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.2460. Min Act: -0.0000

Data Index: 860134 (The Pile)

Max Activating Token Index: 892

Text #14

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.1684. Min Act: -0.0000

Data Index: 607746 (The Pile)

Max Activating Token Index: 767

Text #15

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.3921. Min Act: -0.0000

Data Index: 387967 (The Pile)

Max Activating Token Index: 248

Text #16

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.4756. Min Act: -0.0000

Data Index: 1328130 (The Pile)

Max Activating Token Index: 935

Text #17

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.3077. Min Act: -0.0000

Data Index: 936878 (The Pile)

Max Activating Token Index: 746

Text #18

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.2953. Min Act: -0.0000

Data Index: 825017 (The Pile)

Max Activating Token Index: 284

Text #19

Max Range: 1.9299. Min Range: -1.9299

Max Act: 1.3569. Min Act: -0.0000

Data Index: 1741471 (The Pile)

Max Activating Token Index: 687