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

Dataset: The Pile

Neuron 795 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: 0.1799. Min Range: -0.1799

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1569398 (The Pile)

Max Activating Token Index: 968

Text #1

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1568. Min Act: -0.0000

Data Index: 3439 (The Pile)

Max Activating Token Index: 815

Text #2

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1746. Min Act: -0.0000

Data Index: 663783 (The Pile)

Max Activating Token Index: 713

Text #3

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1442. Min Act: -0.0000

Data Index: 846140 (The Pile)

Max Activating Token Index: 226

Text #4

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1336. Min Act: -0.0000

Data Index: 882383 (The Pile)

Max Activating Token Index: 983

Text #5

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1476. Min Act: -0.0000

Data Index: 425667 (The Pile)

Max Activating Token Index: 568

Text #6

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1314. Min Act: -0.0000

Data Index: 906879 (The Pile)

Max Activating Token Index: 930

Text #7

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1528863 (The Pile)

Max Activating Token Index: 911

Text #8

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1257. Min Act: -0.0000

Data Index: 137282 (The Pile)

Max Activating Token Index: 819

Text #9

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1233. Min Act: -0.0000

Data Index: 967401 (The Pile)

Max Activating Token Index: 978

Text #10

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1011. Min Act: -0.0000

Data Index: 325343 (The Pile)

Max Activating Token Index: 945

Text #11

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1332. Min Act: -0.0000

Data Index: 844185 (The Pile)

Max Activating Token Index: 738

Text #12

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1423. Min Act: -0.0000

Data Index: 732090 (The Pile)

Max Activating Token Index: 284

Text #13

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1320. Min Act: -0.0000

Data Index: 146965 (The Pile)

Max Activating Token Index: 1000

Text #14

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1246. Min Act: -0.0000

Data Index: 128969 (The Pile)

Max Activating Token Index: 970

Text #15

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1220. Min Act: -0.0000

Data Index: 11364 (The Pile)

Max Activating Token Index: 428

Text #16

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1150. Min Act: -0.0000

Data Index: 70136 (The Pile)

Max Activating Token Index: 931

Text #17

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1089. Min Act: -0.0000

Data Index: 1392300 (The Pile)

Max Activating Token Index: 900

Text #18

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1131. Min Act: -0.0000

Data Index: 905610 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1599784 (The Pile)

Max Activating Token Index: 829