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

Dataset: The Pile

Neuron 1019 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3017. Min Range: -4.3017

Max Act: 4.0225. Min Act: -0.0000

Data Index: 391665 (The Pile)

Max Activating Token Index: 932

Text #1

Max Range: 4.3017. Min Range: -4.3017

Max Act: 3.8265. Min Act: -0.0000

Data Index: 1150291 (The Pile)

Max Activating Token Index: 874

Text #2

Max Range: 4.3017. Min Range: -4.3017

Max Act: 3.6622. Min Act: -0.0000

Data Index: 1250595 (The Pile)

Max Activating Token Index: 983

Text #3

Max Range: 4.3017. Min Range: -4.3017

Max Act: 4.3017. Min Act: -0.0000

Data Index: 687087 (The Pile)

Max Activating Token Index: 916

Text #4

Max Range: 4.3017. Min Range: -4.3017

Max Act: 3.9865. Min Act: -0.0000

Data Index: 907676 (The Pile)

Max Activating Token Index: 908

Text #5

Max Range: 4.3017. Min Range: -4.3017

Max Act: 4.2206. Min Act: -0.0000

Data Index: 1767031 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 4.3017. Min Range: -4.3017

Max Act: 3.7010. Min Act: -0.0000

Data Index: 1647390 (The Pile)

Max Activating Token Index: 983

Text #7

Max Range: 4.3017. Min Range: -4.3017

Max Act: 3.8624. Min Act: -0.0000

Data Index: 299859 (The Pile)

Max Activating Token Index: 962

Text #8

Max Range: 4.3017. Min Range: -4.3017

Max Act: 3.7121. Min Act: -0.0000

Data Index: 869881 (The Pile)

Max Activating Token Index: 1013

Text #9

Max Range: 4.3017. Min Range: -4.3017

Max Act: 3.8400. Min Act: -0.0000

Data Index: 262271 (The Pile)

Max Activating Token Index: 1008

Text #10

Max Range: 4.3017. Min Range: -4.3017

Max Act: 3.9711. Min Act: -0.0000

Data Index: 189640 (The Pile)

Max Activating Token Index: 957

Text #11

Max Range: 4.3017. Min Range: -4.3017

Max Act: 3.8926. Min Act: -0.0000

Data Index: 240821 (The Pile)

Max Activating Token Index: 875

Text #12

Max Range: 4.3017. Min Range: -4.3017

Max Act: 3.7986. Min Act: -0.0000

Data Index: 314543 (The Pile)

Max Activating Token Index: 915

Text #13

Max Range: 4.3017. Min Range: -4.3017

Max Act: 3.5213. Min Act: -0.0000

Data Index: 1044120 (The Pile)

Max Activating Token Index: 1003

Text #14

Max Range: 4.3017. Min Range: -4.3017

Max Act: 3.9275. Min Act: -0.0000

Data Index: 1894127 (The Pile)

Max Activating Token Index: 837

Text #15

Max Range: 4.3017. Min Range: -4.3017

Max Act: 3.9701. Min Act: -0.0000

Data Index: 764575 (The Pile)

Max Activating Token Index: 909

Text #16

Max Range: 4.3017. Min Range: -4.3017

Max Act: 3.6562. Min Act: -0.0000

Data Index: 639389 (The Pile)

Max Activating Token Index: 948

Text #17

Max Range: 4.3017. Min Range: -4.3017

Max Act: 3.7494. Min Act: -0.0000

Data Index: 608373 (The Pile)

Max Activating Token Index: 959

Text #18

Max Range: 4.3017. Min Range: -4.3017

Max Act: 3.4262. Min Act: -0.0000

Data Index: 1267813 (The Pile)

Max Activating Token Index: 874

Text #19

Max Range: 4.3017. Min Range: -4.3017

Max Act: 3.5654. Min Act: -0.0000

Data Index: 1386609 (The Pile)

Max Activating Token Index: 698