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

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

Neuron 464 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: 0.3232. Min Range: -0.3232

Max Act: 0.3232. Min Act: -0.0000

Data Index: 658086 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2984. Min Act: -0.0001

Data Index: 1121028 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2899. Min Act: -0.0001

Data Index: 1405294 (Python Code)

Max Activating Token Index: 805

Text #3

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2641. Min Act: -0.0001

Data Index: 1565247 (Python Code)

Max Activating Token Index: 164

Text #4

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2785. Min Act: -0.0001

Data Index: 1496935 (Python Code)

Max Activating Token Index: 660

Text #5

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2698. Min Act: -0.0001

Data Index: 695574 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2755. Min Act: -0.0001

Data Index: 1557932 (Python Code)

Max Activating Token Index: 323

Text #7

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2594. Min Act: -0.0001

Data Index: 1375817 (Python Code)

Max Activating Token Index: 579

Text #8

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2404. Min Act: -0.0001

Data Index: 1558454 (Python Code)

Max Activating Token Index: 966

Text #9

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2535. Min Act: -0.0001

Data Index: 1481275 (Python Code)

Max Activating Token Index: 971

Text #10

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2502. Min Act: -0.0001

Data Index: 1459304 (Python Code)

Max Activating Token Index: 483

Text #11

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2480. Min Act: -0.0001

Data Index: 1626775 (Python Code)

Max Activating Token Index: 918

Text #12

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2448. Min Act: -0.0001

Data Index: 1469114 (Python Code)

Max Activating Token Index: 429

Text #13

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2521. Min Act: -0.0001

Data Index: 1416478 (Python Code)

Max Activating Token Index: 623

Text #14

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2622. Min Act: -0.0001

Data Index: 1407222 (Python Code)

Max Activating Token Index: 769

Text #15

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2116. Min Act: -0.0001

Data Index: 1582865 (Python Code)

Max Activating Token Index: 599

Text #16

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2603. Min Act: -0.0001

Data Index: 501384 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2377. Min Act: -0.0001

Data Index: 1425039 (Python Code)

Max Activating Token Index: 880

Text #18

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2243. Min Act: -0.0001

Data Index: 1267987 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2560. Min Act: -0.0001

Data Index: 1425757 (Python Code)

Max Activating Token Index: 924