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

Dataset: The Pile

Neuron 25 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1458553 (The Pile)

Max Activating Token Index: 27

Text #1

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2593. Min Act: -0.0000

Data Index: 585948 (The Pile)

Max Activating Token Index: 995

Text #2

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2260. Min Act: -0.0000

Data Index: 1551165 (The Pile)

Max Activating Token Index: 582

Text #3

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2383. Min Act: -0.0000

Data Index: 1152835 (The Pile)

Max Activating Token Index: 325

Text #4

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2223. Min Act: -0.0000

Data Index: 1087155 (The Pile)

Max Activating Token Index: 352

Text #5

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2138. Min Act: -0.0000

Data Index: 568029 (The Pile)

Max Activating Token Index: 360

Text #6

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1738040 (The Pile)

Max Activating Token Index: 258

Text #7

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2087. Min Act: -0.0000

Data Index: 951596 (The Pile)

Max Activating Token Index: 901

Text #8

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1208707 (The Pile)

Max Activating Token Index: 919

Text #9

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2124. Min Act: -0.0000

Data Index: 866973 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2063. Min Act: -0.0000

Data Index: 112366 (The Pile)

Max Activating Token Index: 493

Text #11

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1591637 (The Pile)

Max Activating Token Index: 444

Text #12

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2087. Min Act: -0.0000

Data Index: 681025 (The Pile)

Max Activating Token Index: 87

Text #13

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1945. Min Act: -0.0000

Data Index: 448327 (The Pile)

Max Activating Token Index: 833

Text #14

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1965. Min Act: -0.0000

Data Index: 342654 (The Pile)

Max Activating Token Index: 128

Text #15

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1803. Min Act: -0.0000

Data Index: 805640 (The Pile)

Max Activating Token Index: 530

Text #16

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1725. Min Act: 0.0000

Data Index: 1552457 (The Pile)

Max Activating Token Index: 1014

Text #17

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1768. Min Act: -0.0000

Data Index: 262013 (The Pile)

Max Activating Token Index: 272

Text #18

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1904. Min Act: -0.0000

Data Index: 439275 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1840. Min Act: -0.0000

Data Index: 787086 (The Pile)

Max Activating Token Index: 779