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

Dataset: The Pile

Neuron 3149 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1455414 (The Pile)

Max Activating Token Index: 432

Text #1

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.8063. Min Act: -0.0000

Data Index: 1522073 (The Pile)

Max Activating Token Index: 766

Text #2

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.7471. Min Act: -0.0000

Data Index: 1094112 (The Pile)

Max Activating Token Index: 544

Text #3

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.7094. Min Act: -0.0000

Data Index: 1784210 (The Pile)

Max Activating Token Index: 330

Text #4

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6708. Min Act: -0.0000

Data Index: 867703 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.7127. Min Act: -0.0000

Data Index: 509934 (The Pile)

Max Activating Token Index: 990

Text #6

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6547. Min Act: -0.0000

Data Index: 223369 (The Pile)

Max Activating Token Index: 104

Text #7

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1583916 (The Pile)

Max Activating Token Index: 131

Text #8

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1748052 (The Pile)

Max Activating Token Index: 1017

Text #9

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1415960 (The Pile)

Max Activating Token Index: 192

Text #10

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6670. Min Act: -0.0000

Data Index: 1121204 (The Pile)

Max Activating Token Index: 1019

Text #11

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6110. Min Act: -0.0000

Data Index: 867847 (The Pile)

Max Activating Token Index: 761

Text #12

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5294. Min Act: -0.0000

Data Index: 757777 (The Pile)

Max Activating Token Index: 721

Text #13

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6336. Min Act: -0.0000

Data Index: 135961 (The Pile)

Max Activating Token Index: 292

Text #14

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5560. Min Act: -0.0000

Data Index: 284660 (The Pile)

Max Activating Token Index: 201

Text #15

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1055466 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1559191 (The Pile)

Max Activating Token Index: 971

Text #17

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6303. Min Act: -0.0000

Data Index: 977997 (The Pile)

Max Activating Token Index: 670

Text #18

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6628. Min Act: -0.0000

Data Index: 516936 (The Pile)

Max Activating Token Index: 205

Text #19

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6174. Min Act: -0.0000

Data Index: 1004156 (The Pile)

Max Activating Token Index: 117