Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2108 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.6430. Min Act: -0.0000

Data Index: 1488191 (Python Code)

Max Activating Token Index: 301

Text #1

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.5505. Min Act: -0.0000

Data Index: 1560519 (Python Code)

Max Activating Token Index: 507

Text #2

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.5348. Min Act: -0.0000

Data Index: 1522702 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.4663. Min Act: -0.0000

Data Index: 1648373 (Python Code)

Max Activating Token Index: 864

Text #4

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.4364. Min Act: -0.0000

Data Index: 1415677 (Python Code)

Max Activating Token Index: 901

Text #5

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.3034. Min Act: -0.0000

Data Index: 1647932 (Python Code)

Max Activating Token Index: 975

Text #6

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.4473. Min Act: -0.0000

Data Index: 1409065 (Python Code)

Max Activating Token Index: 821

Text #7

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.4884. Min Act: -0.0000

Data Index: 1461724 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.4884. Min Act: -0.0000

Data Index: 1570817 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.4884. Min Act: -0.0000

Data Index: 1574949 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.4455. Min Act: -0.0000

Data Index: 1554881 (Python Code)

Max Activating Token Index: 403

Text #11

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.3963. Min Act: -0.0000

Data Index: 1480911 (Python Code)

Max Activating Token Index: 117

Text #12

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.4009. Min Act: -0.0000

Data Index: 1587895 (Python Code)

Max Activating Token Index: 281

Text #13

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.3855. Min Act: -0.0000

Data Index: 1573483 (Python Code)

Max Activating Token Index: 5

Text #14

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.4209. Min Act: -0.0000

Data Index: 1616926 (Python Code)

Max Activating Token Index: 25

Text #15

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.4315. Min Act: -0.0000

Data Index: 1573111 (Python Code)

Max Activating Token Index: 589

Text #16

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.3161. Min Act: -0.0001

Data Index: 1462750 (Python Code)

Max Activating Token Index: 232

Text #17

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.3447. Min Act: -0.0000

Data Index: 1457994 (Python Code)

Max Activating Token Index: 5

Text #18

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.3254. Min Act: -0.0000

Data Index: 1405892 (Python Code)

Max Activating Token Index: 1013

Text #19

Max Range: 1.6430. Min Range: -1.6430

Max Act: 1.3434. Min Act: -0.0000

Data Index: 1440292 (Python Code)

Max Activating Token Index: 6