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

Dataset: The Pile

Neuron 15 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.7124. Min Act: -0.0000

Data Index: 1094917 (The Pile)

Max Activating Token Index: 982

Text #1

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.4746. Min Act: -0.0000

Data Index: 884015 (The Pile)

Max Activating Token Index: 69

Text #2

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.3799. Min Act: -0.0000

Data Index: 761321 (The Pile)

Max Activating Token Index: 723

Text #3

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.4438. Min Act: -0.0000

Data Index: 758508 (The Pile)

Max Activating Token Index: 811

Text #4

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.3060. Min Act: -0.0000

Data Index: 1017437 (The Pile)

Max Activating Token Index: 789

Text #5

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.3774. Min Act: -0.0000

Data Index: 160699 (The Pile)

Max Activating Token Index: 1019

Text #6

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.4730. Min Act: -0.0000

Data Index: 346240 (The Pile)

Max Activating Token Index: 841

Text #7

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.3988. Min Act: -0.0000

Data Index: 224303 (The Pile)

Max Activating Token Index: 14

Text #8

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.2027. Min Act: -0.0000

Data Index: 646955 (The Pile)

Max Activating Token Index: 577

Text #9

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.2381. Min Act: -0.0000

Data Index: 597846 (The Pile)

Max Activating Token Index: 111

Text #10

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.2725. Min Act: -0.0000

Data Index: 566877 (The Pile)

Max Activating Token Index: 587

Text #11

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.2580. Min Act: -0.0000

Data Index: 564727 (The Pile)

Max Activating Token Index: 374

Text #12

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.2013. Min Act: -0.0000

Data Index: 484111 (The Pile)

Max Activating Token Index: 547

Text #13

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.1833. Min Act: -0.0000

Data Index: 1872782 (The Pile)

Max Activating Token Index: 545

Text #14

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.2278. Min Act: -0.0000

Data Index: 1739213 (The Pile)

Max Activating Token Index: 255

Text #15

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.1921. Min Act: -0.0000

Data Index: 572984 (The Pile)

Max Activating Token Index: 477

Text #16

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.1212. Min Act: -0.0000

Data Index: 1661211 (The Pile)

Max Activating Token Index: 896

Text #17

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.1459. Min Act: -0.0000

Data Index: 1676909 (The Pile)

Max Activating Token Index: 31

Text #18

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.2135. Min Act: -0.0000

Data Index: 1414599 (The Pile)

Max Activating Token Index: 578

Text #19

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.2054. Min Act: -0.0000

Data Index: 465457 (The Pile)

Max Activating Token Index: 447