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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1634 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0069. Min Range: -1.0069

Max Act: 1.0069. Min Act: -0.0001

Data Index: 721718 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8843. Min Act: -0.0001

Data Index: 655908 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.9373. Min Act: -0.0001

Data Index: 882817 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.9910. Min Act: -0.0001

Data Index: 730793 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8079. Min Act: -0.0001

Data Index: 437455 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8092. Min Act: -0.0001

Data Index: 1180193 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7685. Min Act: -0.0001

Data Index: 361865 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8076. Min Act: -0.0001

Data Index: 410010 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.6115. Min Act: -0.0001

Data Index: 1162782 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7612. Min Act: -0.0001

Data Index: 195113 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8137. Min Act: -0.0001

Data Index: 1244152 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8093. Min Act: -0.0001

Data Index: 111854 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.5981. Min Act: -0.0001

Data Index: 1149989 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7330. Min Act: -0.0001

Data Index: 1342279 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.6934. Min Act: -0.0001

Data Index: 261664 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7037. Min Act: -0.0001

Data Index: 825401 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7439. Min Act: -0.0001

Data Index: 366371 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7293. Min Act: -0.0001

Data Index: 714655 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7013. Min Act: -0.0001

Data Index: 627122 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7920. Min Act: -0.0001

Data Index: 206309 (C4 (Web Text))

Max Activating Token Index: 739