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

Dataset: The Pile

Neuron 2883 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: 0.2557. Min Range: -0.2557

Max Act: 0.2557. Min Act: -0.0000

Data Index: 1784805 (The Pile)

Max Activating Token Index: 360

Text #1

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2427. Min Act: -0.0000

Data Index: 237508 (The Pile)

Max Activating Token Index: 682

Text #2

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1343969 (The Pile)

Max Activating Token Index: 515

Text #3

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2392. Min Act: -0.0000

Data Index: 347874 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1064853 (The Pile)

Max Activating Token Index: 256

Text #5

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2376. Min Act: -0.0000

Data Index: 13386 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2279. Min Act: -0.0000

Data Index: 1521677 (The Pile)

Max Activating Token Index: 710

Text #7

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2260. Min Act: -0.0000

Data Index: 1847660 (The Pile)

Max Activating Token Index: 632

Text #8

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2188. Min Act: -0.0000

Data Index: 365509 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1244749 (The Pile)

Max Activating Token Index: 799

Text #10

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2157. Min Act: -0.0000

Data Index: 733660 (The Pile)

Max Activating Token Index: 608

Text #11

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1578033 (The Pile)

Max Activating Token Index: 1002

Text #12

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2129. Min Act: -0.0000

Data Index: 391464 (The Pile)

Max Activating Token Index: 967

Text #13

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2426. Min Act: -0.0000

Data Index: 629301 (The Pile)

Max Activating Token Index: 681

Text #14

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1641636 (The Pile)

Max Activating Token Index: 813

Text #15

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2147. Min Act: -0.0000

Data Index: 1327851 (The Pile)

Max Activating Token Index: 830

Text #16

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2132. Min Act: -0.0000

Data Index: 84837 (The Pile)

Max Activating Token Index: 383

Text #17

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2192. Min Act: -0.0000

Data Index: 756275 (The Pile)

Max Activating Token Index: 897

Text #18

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1569074 (The Pile)

Max Activating Token Index: 668

Text #19

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2118. Min Act: -0.0000

Data Index: 1616503 (The Pile)

Max Activating Token Index: 321