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

Dataset: The Pile

Neuron 4124 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1258433 (The Pile)

Max Activating Token Index: 987

Text #1

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2706. Min Act: -0.0000

Data Index: 1218543 (The Pile)

Max Activating Token Index: 676

Text #2

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2356. Min Act: -0.0000

Data Index: 1244133 (The Pile)

Max Activating Token Index: 483

Text #3

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1000901 (The Pile)

Max Activating Token Index: 900

Text #4

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2293. Min Act: -0.0000

Data Index: 1076013 (The Pile)

Max Activating Token Index: 911

Text #5

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1097595 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2283. Min Act: -0.0000

Data Index: 50973 (The Pile)

Max Activating Token Index: 427

Text #7

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2222. Min Act: -0.0000

Data Index: 140268 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1536870 (The Pile)

Max Activating Token Index: 992

Text #9

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2336. Min Act: -0.0000

Data Index: 1717744 (The Pile)

Max Activating Token Index: 999

Text #10

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1756417 (The Pile)

Max Activating Token Index: 592

Text #11

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2324. Min Act: -0.0000

Data Index: 1480654 (The Pile)

Max Activating Token Index: 697

Text #12

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2298. Min Act: -0.0000

Data Index: 527718 (The Pile)

Max Activating Token Index: 940

Text #13

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1772382 (The Pile)

Max Activating Token Index: 204

Text #14

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2039. Min Act: -0.0000

Data Index: 710755 (The Pile)

Max Activating Token Index: 942

Text #15

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1289512 (The Pile)

Max Activating Token Index: 393

Text #16

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1569043 (The Pile)

Max Activating Token Index: 713

Text #17

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.1960. Min Act: -0.0000

Data Index: 787258 (The Pile)

Max Activating Token Index: 865

Text #18

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1442756 (The Pile)

Max Activating Token Index: 260

Text #19

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.1989. Min Act: -0.0000

Data Index: 810847 (The Pile)

Max Activating Token Index: 695