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

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

Neuron 3652 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: 3.1243. Min Range: -3.1243

Max Act: 3.1243. Min Act: -0.0001

Data Index: 441983 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 3.1243. Min Range: -3.1243

Max Act: 3.0435. Min Act: -0.0000

Data Index: 904771 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 3.1243. Min Range: -3.1243

Max Act: 2.8938. Min Act: -0.0001

Data Index: 509000 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 3.1243. Min Range: -3.1243

Max Act: 2.8697. Min Act: -0.0001

Data Index: 757223 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 3.1243. Min Range: -3.1243

Max Act: 2.5256. Min Act: -0.0001

Data Index: 303409 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 3.1243. Min Range: -3.1243

Max Act: 2.7124. Min Act: -0.0000

Data Index: 1134329 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 3.1243. Min Range: -3.1243

Max Act: 2.5564. Min Act: -0.0001

Data Index: 1386570 (Python Code)

Max Activating Token Index: 29

Text #7

Max Range: 3.1243. Min Range: -3.1243

Max Act: 2.2739. Min Act: -0.0001

Data Index: 101203 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 3.1243. Min Range: -3.1243

Max Act: 2.4714. Min Act: -0.0000

Data Index: 1018846 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 3.1243. Min Range: -3.1243

Max Act: 2.3889. Min Act: -0.0001

Data Index: 1068051 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 3.1243. Min Range: -3.1243

Max Act: 2.2251. Min Act: -0.0001

Data Index: 134061 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 3.1243. Min Range: -3.1243

Max Act: 2.2952. Min Act: -0.0000

Data Index: 1067142 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 3.1243. Min Range: -3.1243

Max Act: 2.1657. Min Act: -0.0001

Data Index: 836162 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 3.1243. Min Range: -3.1243

Max Act: 2.1234. Min Act: -0.0001

Data Index: 411163 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 3.1243. Min Range: -3.1243

Max Act: 2.2354. Min Act: -0.0001

Data Index: 1075253 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 3.1243. Min Range: -3.1243

Max Act: 2.1045. Min Act: -0.0001

Data Index: 1586297 (Python Code)

Max Activating Token Index: 358

Text #16

Max Range: 3.1243. Min Range: -3.1243

Max Act: 1.9915. Min Act: -0.0001

Data Index: 259431 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 3.1243. Min Range: -3.1243

Max Act: 2.0015. Min Act: -0.0001

Data Index: 1625256 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 3.1243. Min Range: -3.1243

Max Act: 1.9740. Min Act: -0.0001

Data Index: 842271 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 3.1243. Min Range: -3.1243

Max Act: 2.0563. Min Act: -0.0000

Data Index: 242418 (C4 (Web Text))

Max Activating Token Index: 82