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

Dataset: The Pile

Neuron 164 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3704. Min Act: -0.0000

Data Index: 615603 (The Pile)

Max Activating Token Index: 963

Text #1

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3390. Min Act: -0.0000

Data Index: 1383810 (The Pile)

Max Activating Token Index: 630

Text #2

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1781947 (The Pile)

Max Activating Token Index: 699

Text #3

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2884. Min Act: -0.0000

Data Index: 1092788 (The Pile)

Max Activating Token Index: 240

Text #4

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1980346 (The Pile)

Max Activating Token Index: 202

Text #5

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2688. Min Act: -0.0000

Data Index: 724215 (The Pile)

Max Activating Token Index: 622

Text #6

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1727988 (The Pile)

Max Activating Token Index: 859

Text #7

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2593. Min Act: -0.0000

Data Index: 597425 (The Pile)

Max Activating Token Index: 250

Text #8

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2503. Min Act: -0.0000

Data Index: 87057 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2672. Min Act: -0.0000

Data Index: 1147727 (The Pile)

Max Activating Token Index: 257

Text #10

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2555. Min Act: -0.0000

Data Index: 846985 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1795101 (The Pile)

Max Activating Token Index: 637

Text #12

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1801747 (The Pile)

Max Activating Token Index: 421

Text #13

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2204. Min Act: -0.0000

Data Index: 745310 (The Pile)

Max Activating Token Index: 989

Text #14

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2103. Min Act: -0.0000

Data Index: 125406 (The Pile)

Max Activating Token Index: 605

Text #15

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2116. Min Act: -0.0000

Data Index: 687949 (The Pile)

Max Activating Token Index: 892

Text #16

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2174. Min Act: -0.0000

Data Index: 1775104 (The Pile)

Max Activating Token Index: 371

Text #17

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2237. Min Act: -0.0000

Data Index: 486961 (The Pile)

Max Activating Token Index: 343

Text #18

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2089. Min Act: -0.0000

Data Index: 37031 (The Pile)

Max Activating Token Index: 671

Text #19

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.2331. Min Act: -0.0000

Data Index: 136810 (The Pile)

Max Activating Token Index: 242