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

Dataset: The Pile

Neuron 135 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: 0.5029. Min Range: -0.5029

Max Act: 0.4950. Min Act: -0.0000

Data Index: 500146 (The Pile)

Max Activating Token Index: 113

Text #1

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.5029. Min Act: -0.0000

Data Index: 196442 (The Pile)

Max Activating Token Index: 463

Text #2

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1918101 (The Pile)

Max Activating Token Index: 848

Text #3

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1881000 (The Pile)

Max Activating Token Index: 466

Text #4

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1642189 (The Pile)

Max Activating Token Index: 49

Text #5

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1088922 (The Pile)

Max Activating Token Index: 160

Text #6

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4229. Min Act: -0.0000

Data Index: 520364 (The Pile)

Max Activating Token Index: 986

Text #7

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4249. Min Act: -0.0000

Data Index: 549426 (The Pile)

Max Activating Token Index: 703

Text #8

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1294880 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4224. Min Act: -0.0000

Data Index: 1072824 (The Pile)

Max Activating Token Index: 860

Text #10

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4033. Min Act: -0.0000

Data Index: 470471 (The Pile)

Max Activating Token Index: 753

Text #11

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1658513 (The Pile)

Max Activating Token Index: 209

Text #12

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4081. Min Act: -0.0000

Data Index: 1303457 (The Pile)

Max Activating Token Index: 531

Text #13

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4095. Min Act: -0.0000

Data Index: 82430 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4091. Min Act: -0.0000

Data Index: 907852 (The Pile)

Max Activating Token Index: 384

Text #15

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4316. Min Act: -0.0000

Data Index: 148522 (The Pile)

Max Activating Token Index: 1019

Text #16

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4220. Min Act: -0.0000

Data Index: 792118 (The Pile)

Max Activating Token Index: 325

Text #17

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4174. Min Act: -0.0000

Data Index: 511051 (The Pile)

Max Activating Token Index: 684

Text #18

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1679533 (The Pile)

Max Activating Token Index: 182

Text #19

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.4142. Min Act: -0.0000

Data Index: 718583 (The Pile)

Max Activating Token Index: 128