Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2015 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3225. Min Range: -1.3225

Max Act: 1.2616. Min Act: -0.0001

Data Index: 1179689 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 1.3225. Min Range: -1.3225

Max Act: 1.3225. Min Act: -0.0000

Data Index: 967067 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 1.3225. Min Range: -1.3225

Max Act: 1.1270. Min Act: -0.0001

Data Index: 238319 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 1.3225. Min Range: -1.3225

Max Act: 1.1612. Min Act: -0.0000

Data Index: 21855 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 1.3225. Min Range: -1.3225

Max Act: 1.0803. Min Act: -0.0000

Data Index: 1118127 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 1.3225. Min Range: -1.3225

Max Act: 1.0415. Min Act: -0.0000

Data Index: 1293008 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 1.3225. Min Range: -1.3225

Max Act: 1.0344. Min Act: -0.0000

Data Index: 678140 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 1.3225. Min Range: -1.3225

Max Act: 1.0605. Min Act: -0.0000

Data Index: 1150304 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.9662. Min Act: -0.0000

Data Index: 332608 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 1.3225. Min Range: -1.3225

Max Act: 1.0086. Min Act: -0.0000

Data Index: 1008575 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.9751. Min Act: -0.0000

Data Index: 41972 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.9555. Min Act: -0.0000

Data Index: 1194486 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.9198. Min Act: -0.0000

Data Index: 618100 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.9535. Min Act: -0.0000

Data Index: 911174 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.9695. Min Act: -0.0000

Data Index: 693180 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1049022 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.9262. Min Act: -0.0000

Data Index: 529040 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.9359. Min Act: -0.0000

Data Index: 822854 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.9131. Min Act: -0.0000

Data Index: 298004 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.9616. Min Act: -0.0000

Data Index: 948589 (C4 (Web Text))

Max Activating Token Index: 336