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

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

Neuron 1406 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5689. Min Act: -0.0002

Data Index: 504304 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5002. Min Act: -0.0002

Data Index: 904210 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4918. Min Act: -0.0002

Data Index: 1108946 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4643. Min Act: -0.0002

Data Index: 1309722 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3802. Min Act: -0.0002

Data Index: 1344773 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4705. Min Act: -0.0002

Data Index: 1070960 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4725. Min Act: -0.0002

Data Index: 720698 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4863. Min Act: -0.0002

Data Index: 429015 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4707. Min Act: -0.0002

Data Index: 506254 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4250. Min Act: -0.0002

Data Index: 25664 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4661. Min Act: -0.0002

Data Index: 1036061 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4356. Min Act: -0.0002

Data Index: 820129 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4168. Min Act: -0.0002

Data Index: 194975 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4275. Min Act: -0.0002

Data Index: 1236380 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4675. Min Act: -0.0002

Data Index: 329253 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4361. Min Act: -0.0002

Data Index: 636993 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4524. Min Act: -0.0002

Data Index: 1283906 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3990. Min Act: -0.0002

Data Index: 1121263 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4973. Min Act: -0.0002

Data Index: 521011 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4194. Min Act: -0.0002

Data Index: 948098 (C4 (Web Text))

Max Activating Token Index: 632