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

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

Neuron 2445 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.5128. Min Act: -0.0002

Data Index: 925577 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4898. Min Act: -0.0001

Data Index: 282215 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.5397. Min Act: -0.0001

Data Index: 223875 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.5325. Min Act: -0.0001

Data Index: 327232 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4978. Min Act: -0.0002

Data Index: 874854 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4943. Min Act: -0.0001

Data Index: 831522 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.5061. Min Act: -0.0002

Data Index: 832124 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4926. Min Act: -0.0002

Data Index: 234363 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4736. Min Act: -0.0001

Data Index: 1207860 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.5006. Min Act: -0.0002

Data Index: 1318083 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.5167. Min Act: -0.0002

Data Index: 594019 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4940. Min Act: -0.0002

Data Index: 15385 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4894. Min Act: -0.0001

Data Index: 524683 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.5022. Min Act: -0.0002

Data Index: 1073611 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4895. Min Act: -0.0002

Data Index: 914632 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4630. Min Act: -0.0002

Data Index: 1170558 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4762. Min Act: -0.0001

Data Index: 807319 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4555. Min Act: -0.0002

Data Index: 829993 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4834. Min Act: -0.0002

Data Index: 289102 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.5397. Min Range: -0.5397

Max Act: 0.4743. Min Act: -0.0001

Data Index: 231370 (C4 (Web Text))

Max Activating Token Index: 666