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

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

Neuron 1335 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: 0.2652. Min Range: -0.2652

Max Act: 0.2536. Min Act: -0.0001

Data Index: 1566561 (Python Code)

Max Activating Token Index: 354

Text #1

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2263. Min Act: -0.0001

Data Index: 1531365 (Python Code)

Max Activating Token Index: 540

Text #2

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2652. Min Act: -0.0001

Data Index: 1504338 (Python Code)

Max Activating Token Index: 560

Text #3

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2074. Min Act: -0.0001

Data Index: 1463630 (Python Code)

Max Activating Token Index: 978

Text #4

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2017. Min Act: -0.0001

Data Index: 1601634 (Python Code)

Max Activating Token Index: 79

Text #5

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2106. Min Act: -0.0002

Data Index: 1547582 (Python Code)

Max Activating Token Index: 436

Text #6

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.1999. Min Act: -0.0002

Data Index: 1509200 (Python Code)

Max Activating Token Index: 639

Text #7

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2277. Min Act: -0.0001

Data Index: 1641672 (Python Code)

Max Activating Token Index: 470

Text #8

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2061. Min Act: -0.0001

Data Index: 1647575 (Python Code)

Max Activating Token Index: 397

Text #9

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.1875. Min Act: -0.0001

Data Index: 1623785 (Python Code)

Max Activating Token Index: 803

Text #10

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.1936. Min Act: -0.0001

Data Index: 1467530 (Python Code)

Max Activating Token Index: 327

Text #11

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2145. Min Act: -0.0001

Data Index: 1447082 (Python Code)

Max Activating Token Index: 514

Text #12

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.2042. Min Act: -0.0001

Data Index: 1598883 (Python Code)

Max Activating Token Index: 233

Text #13

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.1834. Min Act: -0.0001

Data Index: 1406995 (Python Code)

Max Activating Token Index: 502

Text #14

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.1973. Min Act: -0.0001

Data Index: 1562313 (Python Code)

Max Activating Token Index: 391

Text #15

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.1889. Min Act: -0.0001

Data Index: 1424736 (Python Code)

Max Activating Token Index: 586

Text #16

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.1788. Min Act: -0.0002

Data Index: 1435587 (Python Code)

Max Activating Token Index: 176

Text #17

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.1910. Min Act: -0.0001

Data Index: 1542511 (Python Code)

Max Activating Token Index: 346

Text #18

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.1908. Min Act: -0.0001

Data Index: 1566369 (Python Code)

Max Activating Token Index: 262

Text #19

Max Range: 0.2652. Min Range: -0.2652

Max Act: 0.1831. Min Act: -0.0001

Data Index: 1550128 (Python Code)

Max Activating Token Index: 786