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

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

Neuron 2402 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0162. Min Range: -1.0162

Max Act: 1.0162. Min Act: -0.0001

Data Index: 594036 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.9098. Min Act: -0.0000

Data Index: 735623 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.8228. Min Act: -0.0000

Data Index: 243556 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.7267. Min Act: -0.0001

Data Index: 1102702 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.8917. Min Act: -0.0001

Data Index: 1262288 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.7960. Min Act: -0.0001

Data Index: 1035564 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.8097. Min Act: -0.0000

Data Index: 1022415 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.7582. Min Act: -0.0000

Data Index: 844429 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.7142. Min Act: -0.0000

Data Index: 670079 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.7055. Min Act: -0.0000

Data Index: 180465 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.6576. Min Act: -0.0000

Data Index: 616916 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.6838. Min Act: -0.0000

Data Index: 964337 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.6015. Min Act: -0.0001

Data Index: 725038 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1476926 (Python Code)

Max Activating Token Index: 670

Text #14

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.6993. Min Act: -0.0001

Data Index: 260896 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.6603. Min Act: -0.0000

Data Index: 1156633 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.6127. Min Act: -0.0001

Data Index: 569504 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.5879. Min Act: -0.0000

Data Index: 36109 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.6241. Min Act: -0.0000

Data Index: 994798 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 1.0162. Min Range: -1.0162

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1004122 (C4 (Web Text))

Max Activating Token Index: 354