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

Dataset: The Pile

Neuron 3851 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1040. Min Act: -0.0000

Data Index: 1107506 (The Pile)

Max Activating Token Index: 920

Text #1

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1028. Min Act: -0.0000

Data Index: 1120564 (The Pile)

Max Activating Token Index: 536

Text #2

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1025. Min Act: -0.0000

Data Index: 356397 (The Pile)

Max Activating Token Index: 699

Text #3

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1019. Min Act: -0.0000

Data Index: 109816 (The Pile)

Max Activating Token Index: 572

Text #4

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1063. Min Act: -0.0000

Data Index: 477762 (The Pile)

Max Activating Token Index: 97

Text #5

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1453495 (The Pile)

Max Activating Token Index: 814

Text #6

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1665163 (The Pile)

Max Activating Token Index: 193

Text #7

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0906. Min Act: -0.0000

Data Index: 1045088 (The Pile)

Max Activating Token Index: 16

Text #8

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0901. Min Act: -0.0000

Data Index: 680761 (The Pile)

Max Activating Token Index: 475

Text #9

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0951. Min Act: -0.0000

Data Index: 1096004 (The Pile)

Max Activating Token Index: 101

Text #10

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0981. Min Act: -0.0000

Data Index: 1257431 (The Pile)

Max Activating Token Index: 211

Text #11

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1084575 (The Pile)

Max Activating Token Index: 103

Text #12

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1026636 (The Pile)

Max Activating Token Index: 528

Text #13

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0918. Min Act: -0.0000

Data Index: 397876 (The Pile)

Max Activating Token Index: 607

Text #14

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0952. Min Act: -0.0000

Data Index: 462565 (The Pile)

Max Activating Token Index: 603

Text #15

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0923. Min Act: -0.0001

Data Index: 1393272 (The Pile)

Max Activating Token Index: 946

Text #16

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0916. Min Act: -0.0000

Data Index: 1408102 (The Pile)

Max Activating Token Index: 55

Text #17

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0883. Min Act: -0.0000

Data Index: 875409 (The Pile)

Max Activating Token Index: 25

Text #18

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0943. Min Act: -0.0001

Data Index: 1570167 (The Pile)

Max Activating Token Index: 261

Text #19

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0908. Min Act: -0.0000

Data Index: 298658 (The Pile)

Max Activating Token Index: 1002