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

Dataset: The Pile

Neuron 870 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: 0.2647. Min Range: -0.2647

Max Act: 0.2468. Min Act: -0.0000

Data Index: 1460748 (The Pile)

Max Activating Token Index: 919

Text #1

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1171745 (The Pile)

Max Activating Token Index: 909

Text #2

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2300. Min Act: -0.0000

Data Index: 1580679 (The Pile)

Max Activating Token Index: 233

Text #3

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2319. Min Act: -0.0000

Data Index: 195455 (The Pile)

Max Activating Token Index: 865

Text #4

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2364. Min Act: -0.0000

Data Index: 705362 (The Pile)

Max Activating Token Index: 767

Text #5

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2220. Min Act: -0.0000

Data Index: 563472 (The Pile)

Max Activating Token Index: 459

Text #6

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1955. Min Act: -0.0000

Data Index: 861185 (The Pile)

Max Activating Token Index: 767

Text #7

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2185. Min Act: -0.0000

Data Index: 632936 (The Pile)

Max Activating Token Index: 425

Text #8

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2078. Min Act: -0.0000

Data Index: 43523 (The Pile)

Max Activating Token Index: 109

Text #9

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2087. Min Act: -0.0000

Data Index: 131149 (The Pile)

Max Activating Token Index: 854

Text #10

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2145. Min Act: -0.0000

Data Index: 1032110 (The Pile)

Max Activating Token Index: 662

Text #11

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1982. Min Act: -0.0000

Data Index: 285346 (The Pile)

Max Activating Token Index: 85

Text #12

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1976. Min Act: -0.0000

Data Index: 916950 (The Pile)

Max Activating Token Index: 676

Text #13

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2120. Min Act: -0.0000

Data Index: 902229 (The Pile)

Max Activating Token Index: 443

Text #14

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2223. Min Act: -0.0000

Data Index: 118759 (The Pile)

Max Activating Token Index: 953

Text #15

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2078. Min Act: -0.0000

Data Index: 329230 (The Pile)

Max Activating Token Index: 418

Text #16

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1846. Min Act: -0.0000

Data Index: 29351 (The Pile)

Max Activating Token Index: 305

Text #17

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1820. Min Act: -0.0000

Data Index: 651641 (The Pile)

Max Activating Token Index: 469

Text #18

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1808. Min Act: -0.0000

Data Index: 635906 (The Pile)

Max Activating Token Index: 808

Text #19

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1685. Min Act: -0.0000

Data Index: 961195 (The Pile)

Max Activating Token Index: 905