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

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

Neuron 3988 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.6374. Min Act: -0.0000

Data Index: 251856 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5246. Min Act: -0.0000

Data Index: 916493 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5308. Min Act: -0.0000

Data Index: 428799 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5046. Min Act: -0.0000

Data Index: 416977 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4751. Min Act: -0.0000

Data Index: 729741 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1167823 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4610. Min Act: -0.0000

Data Index: 134324 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4311. Min Act: -0.0000

Data Index: 156775 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4244. Min Act: -0.0000

Data Index: 491973 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4126. Min Act: 0.0001

Data Index: 1347479 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4069. Min Act: -0.0000

Data Index: 136971 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1344125 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4042. Min Act: -0.0000

Data Index: 351483 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.3846. Min Act: -0.0000

Data Index: 27418 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.3836. Min Act: -0.0000

Data Index: 318216 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.3669. Min Act: -0.0000

Data Index: 1127853 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.3729. Min Act: -0.0000

Data Index: 467449 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.3512. Min Act: -0.0000

Data Index: 327099 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.3631. Min Act: -0.0000

Data Index: 990147 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.3502. Min Act: -0.0000

Data Index: 63521 (C4 (Web Text))

Max Activating Token Index: 341