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

Dataset: The Pile

Neuron 926 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: 1.1184. Min Range: -1.1184

Max Act: 1.1165. Min Act: -0.0000

Data Index: 977931 (The Pile)

Max Activating Token Index: 738

Text #1

Max Range: 1.1184. Min Range: -1.1184

Max Act: 1.1184. Min Act: -0.0000

Data Index: 1766456 (The Pile)

Max Activating Token Index: 958

Text #2

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.9867. Min Act: -0.0000

Data Index: 385366 (The Pile)

Max Activating Token Index: 28

Text #3

Max Range: 1.1184. Min Range: -1.1184

Max Act: 1.0596. Min Act: -0.0000

Data Index: 1387941 (The Pile)

Max Activating Token Index: 472

Text #4

Max Range: 1.1184. Min Range: -1.1184

Max Act: 1.0087. Min Act: -0.0000

Data Index: 684898 (The Pile)

Max Activating Token Index: 648

Text #5

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.9524. Min Act: -0.0000

Data Index: 629683 (The Pile)

Max Activating Token Index: 56

Text #6

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.9658. Min Act: -0.0000

Data Index: 553026 (The Pile)

Max Activating Token Index: 334

Text #7

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1807663 (The Pile)

Max Activating Token Index: 33

Text #8

Max Range: 1.1184. Min Range: -1.1184

Max Act: 1.0272. Min Act: -0.0000

Data Index: 304368 (The Pile)

Max Activating Token Index: 779

Text #9

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.9677. Min Act: -0.0000

Data Index: 783159 (The Pile)

Max Activating Token Index: 202

Text #10

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1648923 (The Pile)

Max Activating Token Index: 727

Text #11

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.9178. Min Act: -0.0000

Data Index: 1995990 (The Pile)

Max Activating Token Index: 306

Text #12

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.9066. Min Act: -0.0000

Data Index: 1750487 (The Pile)

Max Activating Token Index: 973

Text #13

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.8662. Min Act: -0.0000

Data Index: 294804 (The Pile)

Max Activating Token Index: 492

Text #14

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.9367. Min Act: -0.0000

Data Index: 1649452 (The Pile)

Max Activating Token Index: 384

Text #15

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.8285. Min Act: -0.0000

Data Index: 574478 (The Pile)

Max Activating Token Index: 622

Text #16

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.8641. Min Act: -0.0000

Data Index: 727017 (The Pile)

Max Activating Token Index: 202

Text #17

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.8829. Min Act: -0.0000

Data Index: 1670403 (The Pile)

Max Activating Token Index: 45

Text #18

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.8598. Min Act: -0.0000

Data Index: 378520 (The Pile)

Max Activating Token Index: 95

Text #19

Max Range: 1.1184. Min Range: -1.1184

Max Act: 0.9074. Min Act: -0.0000

Data Index: 1394808 (The Pile)

Max Activating Token Index: 787