Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 634 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')

Text #0

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1433. Min Act: -0.0000

Data Index: 635946 (The Pile)

Max Activating Token Index: 93

Text #1

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1227. Min Act: -0.0000

Data Index: 984581 (The Pile)

Max Activating Token Index: 592

Text #2

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1105. Min Act: -0.0000

Data Index: 1489166 (The Pile)

Max Activating Token Index: 237

Text #3

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1121400 (The Pile)

Max Activating Token Index: 103

Text #4

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1071. Min Act: -0.0000

Data Index: 129983 (The Pile)

Max Activating Token Index: 670

Text #5

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1410511 (The Pile)

Max Activating Token Index: 411

Text #6

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1045. Min Act: -0.0000

Data Index: 1738760 (The Pile)

Max Activating Token Index: 61

Text #7

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1034. Min Act: -0.0000

Data Index: 305676 (The Pile)

Max Activating Token Index: 255

Text #8

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1176726 (The Pile)

Max Activating Token Index: 194

Text #9

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1637908 (The Pile)

Max Activating Token Index: 230

Text #10

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1022. Min Act: -0.0000

Data Index: 651628 (The Pile)

Max Activating Token Index: 718

Text #11

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1042. Min Act: -0.0000

Data Index: 1022895 (The Pile)

Max Activating Token Index: 382

Text #12

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1042. Min Act: -0.0000

Data Index: 633941 (The Pile)

Max Activating Token Index: 296

Text #13

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1021. Min Act: -0.0000

Data Index: 420924 (The Pile)

Max Activating Token Index: 120

Text #14

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0980. Min Act: -0.0000

Data Index: 1918777 (The Pile)

Max Activating Token Index: 108

Text #15

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0982. Min Act: -0.0000

Data Index: 573271 (The Pile)

Max Activating Token Index: 153

Text #16

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1317538 (The Pile)

Max Activating Token Index: 946

Text #17

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0962. Min Act: -0.0000

Data Index: 1155858 (The Pile)

Max Activating Token Index: 562

Text #18

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0967. Min Act: -0.0000

Data Index: 156657 (The Pile)

Max Activating Token Index: 815

Text #19

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0954. Min Act: -0.0001

Data Index: 181271 (The Pile)

Max Activating Token Index: 140