Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1614 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.6062. Min Act: -0.0000

Data Index: 688973 (The Pile)

Max Activating Token Index: 126

Text #1

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.3267. Min Act: -0.0000

Data Index: 895560 (The Pile)

Max Activating Token Index: 947

Text #2

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.1689. Min Act: -0.0000

Data Index: 96453 (The Pile)

Max Activating Token Index: 650

Text #3

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.2519. Min Act: -0.0000

Data Index: 1030363 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.1461. Min Act: -0.0000

Data Index: 1815306 (The Pile)

Max Activating Token Index: 828

Text #5

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.1365. Min Act: -0.0000

Data Index: 1721198 (The Pile)

Max Activating Token Index: 871

Text #6

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.1329. Min Act: -0.0000

Data Index: 420127 (The Pile)

Max Activating Token Index: 224

Text #7

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.0386. Min Act: -0.0000

Data Index: 770877 (The Pile)

Max Activating Token Index: 87

Text #8

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.1515. Min Act: -0.0000

Data Index: 1908122 (The Pile)

Max Activating Token Index: 757

Text #9

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.0905. Min Act: -0.0000

Data Index: 823220 (The Pile)

Max Activating Token Index: 651

Text #10

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.1945. Min Act: -0.0000

Data Index: 835174 (The Pile)

Max Activating Token Index: 986

Text #11

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.1746. Min Act: -0.0000

Data Index: 832201 (The Pile)

Max Activating Token Index: 389

Text #12

Max Range: 1.6062. Min Range: -1.6062

Max Act: 0.9924. Min Act: -0.0000

Data Index: 751066 (The Pile)

Max Activating Token Index: 221

Text #13

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.0563. Min Act: -0.0000

Data Index: 1850191 (The Pile)

Max Activating Token Index: 133

Text #14

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.1184. Min Act: -0.0000

Data Index: 439676 (The Pile)

Max Activating Token Index: 130

Text #15

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.1214. Min Act: -0.0000

Data Index: 1197933 (The Pile)

Max Activating Token Index: 263

Text #16

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.1141. Min Act: -0.0000

Data Index: 498477 (The Pile)

Max Activating Token Index: 94

Text #17

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.0503. Min Act: -0.0000

Data Index: 119445 (The Pile)

Max Activating Token Index: 677

Text #18

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.0249. Min Act: -0.0000

Data Index: 1932831 (The Pile)

Max Activating Token Index: 611

Text #19

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.1044. Min Act: -0.0000

Data Index: 1704784 (The Pile)

Max Activating Token Index: 688