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

Dataset: The Pile

Neuron 3742 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1825807 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1563. Min Act: 0.0000

Data Index: 1662138 (The Pile)

Max Activating Token Index: 232

Text #2

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1454. Min Act: 0.0000

Data Index: 1139731 (The Pile)

Max Activating Token Index: 699

Text #3

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1579930 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1395. Min Act: 0.0000

Data Index: 1279491 (The Pile)

Max Activating Token Index: 400

Text #5

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1309. Min Act: -0.0000

Data Index: 574056 (The Pile)

Max Activating Token Index: 464

Text #6

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1333. Min Act: -0.0000

Data Index: 405271 (The Pile)

Max Activating Token Index: 758

Text #7

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1374837 (The Pile)

Max Activating Token Index: 378

Text #8

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1279. Min Act: -0.0000

Data Index: 373491 (The Pile)

Max Activating Token Index: 123

Text #9

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1202. Min Act: -0.0000

Data Index: 26594 (The Pile)

Max Activating Token Index: 978

Text #10

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1245. Min Act: -0.0000

Data Index: 718394 (The Pile)

Max Activating Token Index: 818

Text #11

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1101. Min Act: -0.0000

Data Index: 1228960 (The Pile)

Max Activating Token Index: 174

Text #12

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1168. Min Act: -0.0000

Data Index: 1004270 (The Pile)

Max Activating Token Index: 798

Text #13

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1018. Min Act: -0.0000

Data Index: 565679 (The Pile)

Max Activating Token Index: 889

Text #14

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1128. Min Act: 0.0000

Data Index: 1956761 (The Pile)

Max Activating Token Index: 484

Text #15

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1238. Min Act: -0.0000

Data Index: 1287443 (The Pile)

Max Activating Token Index: 731

Text #16

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1118. Min Act: 0.0000

Data Index: 1367578 (The Pile)

Max Activating Token Index: 198

Text #17

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1932185 (The Pile)

Max Activating Token Index: 731

Text #18

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1092. Min Act: -0.0000

Data Index: 103496 (The Pile)

Max Activating Token Index: 790

Text #19

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1158. Min Act: 0.0000

Data Index: 1456712 (The Pile)

Max Activating Token Index: 873