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

Dataset: The Pile

Neuron 2823 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: 0.3788. Min Range: -0.3788

Max Act: 0.3788. Min Act: -0.0000

Data Index: 1122110 (The Pile)

Max Activating Token Index: 557

Text #1

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3508. Min Act: 0.0000

Data Index: 352247 (The Pile)

Max Activating Token Index: 127

Text #2

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3773. Min Act: -0.0000

Data Index: 102970 (The Pile)

Max Activating Token Index: 141

Text #3

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3507. Min Act: -0.0000

Data Index: 667094 (The Pile)

Max Activating Token Index: 309

Text #4

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3178. Min Act: -0.0000

Data Index: 197774 (The Pile)

Max Activating Token Index: 345

Text #5

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3154. Min Act: 0.0000

Data Index: 400914 (The Pile)

Max Activating Token Index: 677

Text #6

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3095. Min Act: -0.0000

Data Index: 258865 (The Pile)

Max Activating Token Index: 425

Text #7

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3119. Min Act: -0.0000

Data Index: 619843 (The Pile)

Max Activating Token Index: 107

Text #8

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1175918 (The Pile)

Max Activating Token Index: 503

Text #9

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1105298 (The Pile)

Max Activating Token Index: 424

Text #10

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2979. Min Act: 0.0000

Data Index: 556162 (The Pile)

Max Activating Token Index: 437

Text #11

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2981. Min Act: -0.0000

Data Index: 921170 (The Pile)

Max Activating Token Index: 211

Text #12

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2852. Min Act: -0.0000

Data Index: 414297 (The Pile)

Max Activating Token Index: 658

Text #13

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2951. Min Act: -0.0000

Data Index: 1052445 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3027. Min Act: -0.0000

Data Index: 1945814 (The Pile)

Max Activating Token Index: 905

Text #15

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2843. Min Act: -0.0000

Data Index: 674063 (The Pile)

Max Activating Token Index: 125

Text #16

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1087128 (The Pile)

Max Activating Token Index: 263

Text #17

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1784603 (The Pile)

Max Activating Token Index: 162

Text #18

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2671. Min Act: -0.0000

Data Index: 428400 (The Pile)

Max Activating Token Index: 82

Text #19

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2852. Min Act: -0.0000

Data Index: 35956 (The Pile)

Max Activating Token Index: 117