Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4252 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1446. Min Act: -0.0000

Data Index: 369336 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1332. Min Act: -0.0000

Data Index: 119801 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1162. Min Act: -0.0000

Data Index: 281088 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1064. Min Act: -0.0000

Data Index: 947546 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1202160 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1047. Min Act: -0.0000

Data Index: 1347679 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0909. Min Act: -0.0000

Data Index: 836886 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1181. Min Act: -0.0000

Data Index: 294355 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0918. Min Act: -0.0000

Data Index: 446836 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1024. Min Act: -0.0000

Data Index: 823063 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1123273 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0874. Min Act: -0.0000

Data Index: 1638846 (Python Code)

Max Activating Token Index: 487

Text #12

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1003129 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0667. Min Act: -0.0000

Data Index: 792138 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0726. Min Act: -0.0000

Data Index: 90999 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0727. Min Act: -0.0000

Data Index: 594044 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0717. Min Act: -0.0000

Data Index: 1009427 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0750. Min Act: -0.0000

Data Index: 1038003 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0638. Min Act: -0.0000

Data Index: 396343 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.0719. Min Act: -0.0000

Data Index: 404112 (C4 (Web Text))

Max Activating Token Index: 288