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

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

Neuron 645 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1428. Min Act: -0.0000

Data Index: 552139 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1232. Min Act: -0.0001

Data Index: 320293 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1187. Min Act: -0.0000

Data Index: 184005 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1053. Min Act: -0.0000

Data Index: 607133 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1274495 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1031. Min Act: -0.0000

Data Index: 943459 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0953. Min Act: -0.0001

Data Index: 456196 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0989. Min Act: -0.0001

Data Index: 182077 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0999. Min Act: -0.0001

Data Index: 80056 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0910. Min Act: -0.0001

Data Index: 873992 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0904. Min Act: -0.0000

Data Index: 514586 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0873. Min Act: -0.0000

Data Index: 1306616 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0922. Min Act: -0.0000

Data Index: 788871 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0967. Min Act: -0.0000

Data Index: 395975 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1191157 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1324080 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0872. Min Act: -0.0001

Data Index: 1177068 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0874. Min Act: -0.0001

Data Index: 1116713 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0870. Min Act: -0.0000

Data Index: 547229 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0836. Min Act: -0.0001

Data Index: 536446 (C4 (Web Text))

Max Activating Token Index: 626