Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2447 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1193093 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1982. Min Act: -0.0001

Data Index: 993983 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1832. Min Act: -0.0001

Data Index: 749910 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1731. Min Act: -0.0001

Data Index: 1095613 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1555. Min Act: -0.0001

Data Index: 1133400 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1450. Min Act: -0.0001

Data Index: 498527 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1585. Min Act: -0.0001

Data Index: 742823 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1517. Min Act: -0.0001

Data Index: 969940 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1544. Min Act: -0.0001

Data Index: 696542 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1466. Min Act: -0.0001

Data Index: 1110600 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1525. Min Act: -0.0001

Data Index: 456405 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1419. Min Act: -0.0001

Data Index: 342915 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1231. Min Act: -0.0001

Data Index: 576323 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1397. Min Act: -0.0001

Data Index: 227199 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1405. Min Act: -0.0001

Data Index: 531013 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1435. Min Act: -0.0001

Data Index: 698073 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1418. Min Act: -0.0001

Data Index: 595954 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1441. Min Act: -0.0001

Data Index: 1083464 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1239. Min Act: -0.0001

Data Index: 880858 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1346. Min Act: -0.0001

Data Index: 185235 (C4 (Web Text))

Max Activating Token Index: 742