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

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

Neuron 4752 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: 0.6828. Min Range: -0.6828

Max Act: 0.6828. Min Act: -0.0000

Data Index: 1581222 (Python Code)

Max Activating Token Index: 135

Text #1

Max Range: 0.6828. Min Range: -0.6828

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1563216 (Python Code)

Max Activating Token Index: 459

Text #2

Max Range: 0.6828. Min Range: -0.6828

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1370001 (Python Code)

Max Activating Token Index: 976

Text #3

Max Range: 0.6828. Min Range: -0.6828

Max Act: 0.5931. Min Act: -0.0000

Data Index: 1566997 (Python Code)

Max Activating Token Index: 983

Text #4

Max Range: 0.6828. Min Range: -0.6828

Max Act: 0.5452. Min Act: -0.0000

Data Index: 1528953 (Python Code)

Max Activating Token Index: 231

Text #5

Max Range: 0.6828. Min Range: -0.6828

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1540196 (Python Code)

Max Activating Token Index: 976

Text #6

Max Range: 0.6828. Min Range: -0.6828

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1493092 (Python Code)

Max Activating Token Index: 489

Text #7

Max Range: 0.6828. Min Range: -0.6828

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1375759 (Python Code)

Max Activating Token Index: 135

Text #8

Max Range: 0.6828. Min Range: -0.6828

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1539373 (Python Code)

Max Activating Token Index: 644

Text #9

Max Range: 0.6828. Min Range: -0.6828

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1400181 (Python Code)

Max Activating Token Index: 885

Text #10

Max Range: 0.6828. Min Range: -0.6828

Max Act: 0.3800. Min Act: -0.0000

Data Index: 1654295 (Python Code)

Max Activating Token Index: 403

Text #11

Max Range: 0.6828. Min Range: -0.6828

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1505497 (Python Code)

Max Activating Token Index: 723

Text #12

Max Range: 0.6828. Min Range: -0.6828

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1552870 (Python Code)

Max Activating Token Index: 105

Text #13

Max Range: 0.6828. Min Range: -0.6828

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1390644 (Python Code)

Max Activating Token Index: 443

Text #14

Max Range: 0.6828. Min Range: -0.6828

Max Act: 0.3412. Min Act: -0.0000

Data Index: 1500384 (Python Code)

Max Activating Token Index: 480

Text #15

Max Range: 0.6828. Min Range: -0.6828

Max Act: 0.3313. Min Act: -0.0000

Data Index: 1490971 (Python Code)

Max Activating Token Index: 609

Text #16

Max Range: 0.6828. Min Range: -0.6828

Max Act: 0.3252. Min Act: -0.0000

Data Index: 1366330 (Python Code)

Max Activating Token Index: 432

Text #17

Max Range: 0.6828. Min Range: -0.6828

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1558972 (Python Code)

Max Activating Token Index: 655

Text #18

Max Range: 0.6828. Min Range: -0.6828

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1460917 (Python Code)

Max Activating Token Index: 71

Text #19

Max Range: 0.6828. Min Range: -0.6828

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1545741 (Python Code)

Max Activating Token Index: 332