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

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

Neuron 615 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: 1.3594. Min Range: -1.3594

Max Act: 1.3594. Min Act: -0.0000

Data Index: 1448690 (Python Code)

Max Activating Token Index: 957

Text #1

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.2219. Min Act: -0.0000

Data Index: 1504544 (Python Code)

Max Activating Token Index: 390

Text #2

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.1381. Min Act: -0.0000

Data Index: 1401912 (Python Code)

Max Activating Token Index: 699

Text #3

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.0807. Min Act: -0.0000

Data Index: 1502435 (Python Code)

Max Activating Token Index: 979

Text #4

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.1371. Min Act: -0.0000

Data Index: 1559047 (Python Code)

Max Activating Token Index: 237

Text #5

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.0565. Min Act: -0.0000

Data Index: 1456314 (Python Code)

Max Activating Token Index: 787

Text #6

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.0515. Min Act: -0.0000

Data Index: 1472212 (Python Code)

Max Activating Token Index: 362

Text #7

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.0679. Min Act: -0.0000

Data Index: 1591444 (Python Code)

Max Activating Token Index: 97

Text #8

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.0387. Min Act: -0.0000

Data Index: 1642532 (Python Code)

Max Activating Token Index: 425

Text #9

Max Range: 1.3594. Min Range: -1.3594

Max Act: 0.9736. Min Act: -0.0000

Data Index: 1400630 (Python Code)

Max Activating Token Index: 723

Text #10

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.0238. Min Act: -0.0000

Data Index: 1488607 (Python Code)

Max Activating Token Index: 854

Text #11

Max Range: 1.3594. Min Range: -1.3594

Max Act: 0.9526. Min Act: -0.0000

Data Index: 1468328 (Python Code)

Max Activating Token Index: 274

Text #12

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.0055. Min Act: -0.0000

Data Index: 1608897 (Python Code)

Max Activating Token Index: 75

Text #13

Max Range: 1.3594. Min Range: -1.3594

Max Act: 0.8955. Min Act: -0.0000

Data Index: 1530218 (Python Code)

Max Activating Token Index: 253

Text #14

Max Range: 1.3594. Min Range: -1.3594

Max Act: 0.9368. Min Act: -0.0000

Data Index: 1469758 (Python Code)

Max Activating Token Index: 682

Text #15

Max Range: 1.3594. Min Range: -1.3594

Max Act: 0.9463. Min Act: -0.0000

Data Index: 1484909 (Python Code)

Max Activating Token Index: 156

Text #16

Max Range: 1.3594. Min Range: -1.3594

Max Act: 0.9421. Min Act: -0.0000

Data Index: 1620255 (Python Code)

Max Activating Token Index: 718

Text #17

Max Range: 1.3594. Min Range: -1.3594

Max Act: 0.9852. Min Act: -0.0000

Data Index: 1384145 (Python Code)

Max Activating Token Index: 809

Text #18

Max Range: 1.3594. Min Range: -1.3594

Max Act: 0.8703. Min Act: -0.0000

Data Index: 1620544 (Python Code)

Max Activating Token Index: 992

Text #19

Max Range: 1.3594. Min Range: -1.3594

Max Act: 0.9213. Min Act: -0.0000

Data Index: 1495938 (Python Code)

Max Activating Token Index: 76