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

Dataset: The Pile

Neuron 2508 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: 1.3275. Min Range: -1.3275

Max Act: 1.3275. Min Act: -0.0000

Data Index: 137506 (The Pile)

Max Activating Token Index: 839

Text #1

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.2914. Min Act: -0.0000

Data Index: 492276 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.1905. Min Act: -0.0000

Data Index: 1674770 (The Pile)

Max Activating Token Index: 746

Text #3

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.1619. Min Act: -0.0000

Data Index: 1691657 (The Pile)

Max Activating Token Index: 770

Text #4

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.1160. Min Act: -0.0000

Data Index: 1304295 (The Pile)

Max Activating Token Index: 825

Text #5

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.1416. Min Act: -0.0000

Data Index: 354800 (The Pile)

Max Activating Token Index: 264

Text #6

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.1978. Min Act: -0.0000

Data Index: 287725 (The Pile)

Max Activating Token Index: 684

Text #7

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.0942. Min Act: -0.0000

Data Index: 65515 (The Pile)

Max Activating Token Index: 991

Text #8

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.0258. Min Act: -0.0000

Data Index: 800513 (The Pile)

Max Activating Token Index: 188

Text #9

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.1248. Min Act: -0.0000

Data Index: 1189964 (The Pile)

Max Activating Token Index: 579

Text #10

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.1140. Min Act: -0.0000

Data Index: 1305148 (The Pile)

Max Activating Token Index: 695

Text #11

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.0889. Min Act: -0.0000

Data Index: 441886 (The Pile)

Max Activating Token Index: 89

Text #12

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1013058 (The Pile)

Max Activating Token Index: 307

Text #13

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.0575. Min Act: -0.0000

Data Index: 694834 (The Pile)

Max Activating Token Index: 876

Text #14

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.0012. Min Act: -0.0000

Data Index: 662598 (The Pile)

Max Activating Token Index: 707

Text #15

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.0944. Min Act: -0.0000

Data Index: 503576 (The Pile)

Max Activating Token Index: 729

Text #16

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.0059. Min Act: -0.0000

Data Index: 1145680 (The Pile)

Max Activating Token Index: 766

Text #17

Max Range: 1.3275. Min Range: -1.3275

Max Act: 0.9895. Min Act: -0.0000

Data Index: 411088 (The Pile)

Max Activating Token Index: 423

Text #18

Max Range: 1.3275. Min Range: -1.3275

Max Act: 0.9947. Min Act: -0.0000

Data Index: 766331 (The Pile)

Max Activating Token Index: 312

Text #19

Max Range: 1.3275. Min Range: -1.3275

Max Act: 0.9832. Min Act: -0.0000

Data Index: 1145122 (The Pile)

Max Activating Token Index: 669