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

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

Neuron 81 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2667. Min Act: -0.0001

Data Index: 761728 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2392. Min Act: -0.0000

Data Index: 554742 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2362. Min Act: -0.0001

Data Index: 662595 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2011. Min Act: -0.0000

Data Index: 579471 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1995. Min Act: -0.0001

Data Index: 175845 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2056. Min Act: -0.0001

Data Index: 947265 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1949. Min Act: -0.0000

Data Index: 347521 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1913. Min Act: -0.0000

Data Index: 785922 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1929. Min Act: -0.0000

Data Index: 866767 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2066. Min Act: -0.0001

Data Index: 333050 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1843. Min Act: -0.0001

Data Index: 286675 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1844. Min Act: -0.0000

Data Index: 1064598 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1773. Min Act: -0.0001

Data Index: 965500 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1870. Min Act: -0.0000

Data Index: 224253 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1950. Min Act: -0.0001

Data Index: 781033 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1707. Min Act: -0.0001

Data Index: 115944 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1884. Min Act: -0.0000

Data Index: 940452 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1695. Min Act: -0.0000

Data Index: 552068 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1693. Min Act: -0.0000

Data Index: 308983 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1662. Min Act: -0.0001

Data Index: 93086 (C4 (Web Text))

Max Activating Token Index: 635