Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1653 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.6360. Min Range: -5.6360

Max Act: 5.6360. Min Act: -0.0000

Data Index: 722479 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 5.6360. Min Range: -5.6360

Max Act: 5.2128. Min Act: -0.0000

Data Index: 953594 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 5.6360. Min Range: -5.6360

Max Act: 5.2166. Min Act: -0.0001

Data Index: 464013 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 5.6360. Min Range: -5.6360

Max Act: 5.5238. Min Act: -0.0000

Data Index: 489740 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 5.6360. Min Range: -5.6360

Max Act: 5.1388. Min Act: -0.0000

Data Index: 740476 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 5.6360. Min Range: -5.6360

Max Act: 4.9027. Min Act: -0.0000

Data Index: 832453 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 5.6360. Min Range: -5.6360

Max Act: 5.0555. Min Act: -0.0000

Data Index: 722268 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 5.6360. Min Range: -5.6360

Max Act: 5.0695. Min Act: -0.0000

Data Index: 1120240 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 5.6360. Min Range: -5.6360

Max Act: 4.9515. Min Act: -0.0000

Data Index: 1170398 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 5.6360. Min Range: -5.6360

Max Act: 4.4445. Min Act: -0.0000

Data Index: 1071335 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 5.6360. Min Range: -5.6360

Max Act: 4.9117. Min Act: -0.0000

Data Index: 1127401 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 5.6360. Min Range: -5.6360

Max Act: 4.7439. Min Act: -0.0001

Data Index: 841886 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 5.6360. Min Range: -5.6360

Max Act: 4.6761. Min Act: -0.0000

Data Index: 1155973 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 5.6360. Min Range: -5.6360

Max Act: 4.6792. Min Act: -0.0000

Data Index: 1208679 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 5.6360. Min Range: -5.6360

Max Act: 5.3817. Min Act: -0.0000

Data Index: 871905 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 5.6360. Min Range: -5.6360

Max Act: 4.7970. Min Act: -0.0000

Data Index: 1122634 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 5.6360. Min Range: -5.6360

Max Act: 4.7397. Min Act: -0.0000

Data Index: 241250 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 5.6360. Min Range: -5.6360

Max Act: 4.5657. Min Act: -0.0000

Data Index: 512783 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 5.6360. Min Range: -5.6360

Max Act: 4.5069. Min Act: -0.0000

Data Index: 10687 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 5.6360. Min Range: -5.6360

Max Act: 4.6409. Min Act: -0.0000

Data Index: 509392 (C4 (Web Text))

Max Activating Token Index: 18