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

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

Neuron 2289 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: 5.5022. Min Range: -5.5022

Max Act: 5.0410. Min Act: -0.0001

Data Index: 873515 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 5.5022. Min Range: -5.5022

Max Act: 4.6092. Min Act: -0.0001

Data Index: 346551 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 5.5022. Min Range: -5.5022

Max Act: 5.5022. Min Act: -0.0001

Data Index: 1218159 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 5.5022. Min Range: -5.5022

Max Act: 4.7932. Min Act: -0.0001

Data Index: 656768 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 5.5022. Min Range: -5.5022

Max Act: 4.9091. Min Act: -0.0001

Data Index: 266070 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 5.5022. Min Range: -5.5022

Max Act: 4.3490. Min Act: -0.0001

Data Index: 788391 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 5.5022. Min Range: -5.5022

Max Act: 4.4756. Min Act: -0.0001

Data Index: 677146 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 5.5022. Min Range: -5.5022

Max Act: 4.5257. Min Act: -0.0000

Data Index: 911699 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 5.5022. Min Range: -5.5022

Max Act: 4.1124. Min Act: -0.0001

Data Index: 1266645 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 5.5022. Min Range: -5.5022

Max Act: 4.3024. Min Act: -0.0001

Data Index: 473446 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 5.5022. Min Range: -5.5022

Max Act: 4.2037. Min Act: -0.0001

Data Index: 536333 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 5.5022. Min Range: -5.5022

Max Act: 3.7792. Min Act: -0.0001

Data Index: 975570 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 5.5022. Min Range: -5.5022

Max Act: 3.8122. Min Act: -0.0001

Data Index: 770038 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 5.5022. Min Range: -5.5022

Max Act: 3.8100. Min Act: -0.0001

Data Index: 1285436 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 5.5022. Min Range: -5.5022

Max Act: 3.6610. Min Act: -0.0000

Data Index: 234300 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 5.5022. Min Range: -5.5022

Max Act: 3.7500. Min Act: -0.0001

Data Index: 604838 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 5.5022. Min Range: -5.5022

Max Act: 3.5784. Min Act: -0.0001

Data Index: 1148248 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 5.5022. Min Range: -5.5022

Max Act: 3.3594. Min Act: -0.0001

Data Index: 153867 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 5.5022. Min Range: -5.5022

Max Act: 3.5120. Min Act: -0.0001

Data Index: 1193157 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 5.5022. Min Range: -5.5022

Max Act: 3.7505. Min Act: -0.0001

Data Index: 1126940 (C4 (Web Text))

Max Activating Token Index: 839