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

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

Neuron 5082 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: 0.2096. Min Range: -0.2096

Max Act: 0.2096. Min Act: -0.0000

Data Index: 675988 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.2091. Min Act: -0.0000

Data Index: 373716 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1153791 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1918. Min Act: -0.0000

Data Index: 781894 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1998. Min Act: -0.0000

Data Index: 15442 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1853. Min Act: -0.0000

Data Index: 727892 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1694. Min Act: -0.0000

Data Index: 781204 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1766. Min Act: -0.0000

Data Index: 973829 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1778. Min Act: -0.0000

Data Index: 418505 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1803. Min Act: -0.0000

Data Index: 381107 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1590. Min Act: -0.0001

Data Index: 1226996 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1596. Min Act: -0.0000

Data Index: 1135082 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1231079 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1357. Min Act: -0.0001

Data Index: 546128 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1241. Min Act: -0.0000

Data Index: 882891 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1604738 (Python Code)

Max Activating Token Index: 412

Text #16

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1290. Min Act: -0.0000

Data Index: 745296 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1203217 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1251. Min Act: -0.0000

Data Index: 1646632 (Python Code)

Max Activating Token Index: 844

Text #19

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1309115 (C4 (Web Text))

Max Activating Token Index: 161