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

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

Neuron 1019 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1543491 (Python Code)

Max Activating Token Index: 89

Text #1

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1678. Min Act: -0.0000

Data Index: 1583902 (Python Code)

Max Activating Token Index: 193

Text #2

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1597339 (Python Code)

Max Activating Token Index: 559

Text #3

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1203. Min Act: -0.0000

Data Index: 460205 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1076. Min Act: -0.0000

Data Index: 954361 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1049. Min Act: -0.0000

Data Index: 904383 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1016. Min Act: -0.0000

Data Index: 134214 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1032. Min Act: -0.0000

Data Index: 536646 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.0988. Min Act: -0.0000

Data Index: 1542881 (Python Code)

Max Activating Token Index: 22

Text #9

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.0966. Min Act: -0.0000

Data Index: 587571 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1515877 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.0933. Min Act: -0.0000

Data Index: 211053 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.0914. Min Act: -0.0000

Data Index: 1142834 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1006. Min Act: -0.0000

Data Index: 1110344 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.0938. Min Act: -0.0000

Data Index: 88663 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.0926. Min Act: -0.0000

Data Index: 318517 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.0960. Min Act: -0.0000

Data Index: 161951 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1472664 (Python Code)

Max Activating Token Index: 338

Text #18

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.0903. Min Act: -0.0000

Data Index: 324141 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.0906. Min Act: -0.0000

Data Index: 731829 (C4 (Web Text))

Max Activating Token Index: 750