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

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

Neuron 3854 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.2001. Min Act: -0.0000

Data Index: 240024 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1977. Min Act: -0.0000

Data Index: 238916 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1927. Min Act: -0.0000

Data Index: 267107 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1850. Min Act: -0.0001

Data Index: 1445669 (Python Code)

Max Activating Token Index: 412

Text #4

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1657. Min Act: -0.0000

Data Index: 1281122 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1765. Min Act: -0.0000

Data Index: 711935 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1661. Min Act: -0.0000

Data Index: 1451302 (Python Code)

Max Activating Token Index: 268

Text #7

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1531. Min Act: -0.0000

Data Index: 939048 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1524. Min Act: -0.0001

Data Index: 951499 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1645692 (Python Code)

Max Activating Token Index: 283

Text #10

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1523933 (Python Code)

Max Activating Token Index: 289

Text #11

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1398895 (Python Code)

Max Activating Token Index: 44

Text #12

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1402. Min Act: -0.0000

Data Index: 1549718 (Python Code)

Max Activating Token Index: 600

Text #13

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1299. Min Act: -0.0000

Data Index: 1101130 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1393. Min Act: -0.0000

Data Index: 833700 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1281. Min Act: -0.0000

Data Index: 820691 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1368. Min Act: -0.0000

Data Index: 1073568 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1508770 (Python Code)

Max Activating Token Index: 73

Text #18

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1226. Min Act: -0.0000

Data Index: 157158 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1601427 (Python Code)

Max Activating Token Index: 410