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

Dataset: The Pile

Neuron 4811 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: 0.2688. Min Range: -0.2688

Max Act: 0.2628. Min Act: -0.0000

Data Index: 397135 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1201616 (The Pile)

Max Activating Token Index: 1004

Text #2

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2688. Min Act: -0.0000

Data Index: 1525642 (The Pile)

Max Activating Token Index: 436

Text #3

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2563. Min Act: -0.0000

Data Index: 1515866 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2382. Min Act: -0.0000

Data Index: 1100797 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2295. Min Act: -0.0000

Data Index: 47558 (The Pile)

Max Activating Token Index: 404

Text #6

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2534. Min Act: -0.0000

Data Index: 776016 (The Pile)

Max Activating Token Index: 915

Text #7

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2460. Min Act: -0.0000

Data Index: 1919290 (The Pile)

Max Activating Token Index: 594

Text #8

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1312656 (The Pile)

Max Activating Token Index: 951

Text #9

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2423. Min Act: -0.0000

Data Index: 913748 (The Pile)

Max Activating Token Index: 874

Text #10

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2306. Min Act: -0.0000

Data Index: 868329 (The Pile)

Max Activating Token Index: 1021

Text #11

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1344235 (The Pile)

Max Activating Token Index: 423

Text #12

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2102. Min Act: -0.0000

Data Index: 929195 (The Pile)

Max Activating Token Index: 800

Text #13

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2291. Min Act: -0.0000

Data Index: 600129 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2300. Min Act: -0.0000

Data Index: 1742068 (The Pile)

Max Activating Token Index: 940

Text #15

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2203. Min Act: -0.0000

Data Index: 914928 (The Pile)

Max Activating Token Index: 828

Text #16

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2057. Min Act: -0.0000

Data Index: 657761 (The Pile)

Max Activating Token Index: 899

Text #17

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1472592 (The Pile)

Max Activating Token Index: 781

Text #18

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2106. Min Act: -0.0000

Data Index: 867540 (The Pile)

Max Activating Token Index: 755

Text #19

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.1976. Min Act: -0.0000

Data Index: 1425000 (The Pile)

Max Activating Token Index: 499