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

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

Neuron 3336 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.9144. Min Act: -0.0000

Data Index: 61869 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.7254. Min Act: -0.0000

Data Index: 188068 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.7452. Min Act: -0.0000

Data Index: 934148 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.6532. Min Act: -0.0000

Data Index: 712257 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.7087. Min Act: -0.0000

Data Index: 898027 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.7416. Min Act: -0.0000

Data Index: 927928 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1288621 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.6590. Min Act: -0.0000

Data Index: 930507 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1086261 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.6373. Min Act: -0.0000

Data Index: 975111 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.6355. Min Act: -0.0000

Data Index: 1105351 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.6508. Min Act: -0.0000

Data Index: 105944 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.6450. Min Act: -0.0000

Data Index: 1154007 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.6086. Min Act: -0.0000

Data Index: 397655 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.6068. Min Act: -0.0000

Data Index: 541755 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.5871. Min Act: -0.0000

Data Index: 750575 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.5645. Min Act: -0.0000

Data Index: 13234 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.5579. Min Act: -0.0000

Data Index: 39621 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.6119. Min Act: -0.0000

Data Index: 1336922 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.5813. Min Act: -0.0000

Data Index: 982368 (C4 (Web Text))

Max Activating Token Index: 100