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

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

Neuron 441 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2353. Min Act: -0.0001

Data Index: 1134334 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1885. Min Act: -0.0001

Data Index: 1212615 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1829. Min Act: -0.0001

Data Index: 785164 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1773. Min Act: -0.0001

Data Index: 719983 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1711. Min Act: -0.0001

Data Index: 114787 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1686. Min Act: -0.0001

Data Index: 484804 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1626. Min Act: -0.0001

Data Index: 380153 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1611. Min Act: -0.0001

Data Index: 1106028 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1585. Min Act: -0.0001

Data Index: 861177 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1467. Min Act: -0.0001

Data Index: 824390 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1496. Min Act: -0.0001

Data Index: 601865 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1478. Min Act: -0.0001

Data Index: 890734 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1544. Min Act: -0.0001

Data Index: 1013290 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1401. Min Act: -0.0001

Data Index: 272095 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1507. Min Act: -0.0001

Data Index: 575857 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1500. Min Act: -0.0001

Data Index: 399211 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1506. Min Act: -0.0001

Data Index: 374669 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1353. Min Act: -0.0001

Data Index: 905792 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1365. Min Act: -0.0001

Data Index: 249596 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1352. Min Act: -0.0001

Data Index: 778979 (C4 (Web Text))

Max Activating Token Index: 945