Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2950 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2956. Min Act: -0.0000

Data Index: 819148 (The Pile)

Max Activating Token Index: 539

Text #1

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1950. Min Act: -0.0000

Data Index: 651828 (The Pile)

Max Activating Token Index: 488

Text #2

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1820. Min Act: -0.0000

Data Index: 782916 (The Pile)

Max Activating Token Index: 841

Text #3

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1875. Min Act: -0.0000

Data Index: 791421 (The Pile)

Max Activating Token Index: 91

Text #4

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1810. Min Act: -0.0000

Data Index: 544160 (The Pile)

Max Activating Token Index: 918

Text #5

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1790. Min Act: -0.0000

Data Index: 653804 (The Pile)

Max Activating Token Index: 399

Text #6

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1790. Min Act: -0.0000

Data Index: 991036 (The Pile)

Max Activating Token Index: 272

Text #7

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1489. Min Act: -0.0000

Data Index: 853632 (The Pile)

Max Activating Token Index: 512

Text #8

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1580. Min Act: -0.0000

Data Index: 1110862 (The Pile)

Max Activating Token Index: 42

Text #9

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1850. Min Act: -0.0000

Data Index: 106109 (The Pile)

Max Activating Token Index: 536

Text #10

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1573. Min Act: -0.0000

Data Index: 37718 (The Pile)

Max Activating Token Index: 921

Text #11

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1729. Min Act: -0.0000

Data Index: 439816 (The Pile)

Max Activating Token Index: 233

Text #12

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1627. Min Act: -0.0000

Data Index: 1274815 (The Pile)

Max Activating Token Index: 873

Text #13

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1618. Min Act: -0.0000

Data Index: 1957617 (The Pile)

Max Activating Token Index: 183

Text #14

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1420. Min Act: -0.0000

Data Index: 846066 (The Pile)

Max Activating Token Index: 20

Text #15

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1813911 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1477. Min Act: -0.0000

Data Index: 905006 (The Pile)

Max Activating Token Index: 782

Text #17

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1511. Min Act: -0.0000

Data Index: 1954097 (The Pile)

Max Activating Token Index: 318

Text #18

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1496. Min Act: -0.0000

Data Index: 437237 (The Pile)

Max Activating Token Index: 865

Text #19

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1715730 (The Pile)

Max Activating Token Index: 502