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

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

Neuron 4142 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2613. Min Range: -1.2613

Max Act: 1.0122. Min Act: -0.0002

Data Index: 1190758 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 1.2613. Min Range: -1.2613

Max Act: 1.2613. Min Act: -0.0002

Data Index: 631910 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 1.2613. Min Range: -1.2613

Max Act: 1.1825. Min Act: -0.0002

Data Index: 404824 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 1.2613. Min Range: -1.2613

Max Act: 1.0998. Min Act: -0.0002

Data Index: 541098 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 1.2613. Min Range: -1.2613

Max Act: 1.0674. Min Act: -0.0002

Data Index: 162388 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 1.2613. Min Range: -1.2613

Max Act: 1.0845. Min Act: -0.0002

Data Index: 833873 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 1.2613. Min Range: -1.2613

Max Act: 1.1136. Min Act: -0.0002

Data Index: 397186 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 1.2613. Min Range: -1.2613

Max Act: 0.9873. Min Act: -0.0003

Data Index: 92884 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 1.2613. Min Range: -1.2613

Max Act: 0.9923. Min Act: -0.0002

Data Index: 550824 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 1.2613. Min Range: -1.2613

Max Act: 1.0231. Min Act: -0.0002

Data Index: 777222 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 1.2613. Min Range: -1.2613

Max Act: 0.9168. Min Act: -0.0002

Data Index: 422996 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 1.2613. Min Range: -1.2613

Max Act: 0.8342. Min Act: -0.0002

Data Index: 1222610 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 1.2613. Min Range: -1.2613

Max Act: 0.8881. Min Act: -0.0002

Data Index: 1259279 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 1.2613. Min Range: -1.2613

Max Act: 1.0095. Min Act: -0.0002

Data Index: 1065791 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 1.2613. Min Range: -1.2613

Max Act: 0.8371. Min Act: -0.0002

Data Index: 202404 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 1.2613. Min Range: -1.2613

Max Act: 0.9602. Min Act: -0.0002

Data Index: 569361 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 1.2613. Min Range: -1.2613

Max Act: 0.9176. Min Act: -0.0002

Data Index: 925515 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 1.2613. Min Range: -1.2613

Max Act: 0.8866. Min Act: -0.0002

Data Index: 677390 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 1.2613. Min Range: -1.2613

Max Act: 0.9067. Min Act: -0.0002

Data Index: 14329 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 1.2613. Min Range: -1.2613

Max Act: 0.8812. Min Act: -0.0002

Data Index: 1290445 (C4 (Web Text))

Max Activating Token Index: 8