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

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

Neuron 1023 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: 1.8973. Min Range: -1.8973

Max Act: 1.8973. Min Act: -0.0001

Data Index: 1515835 (Python Code)

Max Activating Token Index: 161

Text #1

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.6184. Min Act: -0.0000

Data Index: 1523301 (Python Code)

Max Activating Token Index: 825

Text #2

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.6163. Min Act: -0.0001

Data Index: 1375909 (Python Code)

Max Activating Token Index: 307

Text #3

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.6046. Min Act: -0.0000

Data Index: 1388346 (Python Code)

Max Activating Token Index: 408

Text #4

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.4220. Min Act: -0.0000

Data Index: 1441065 (Python Code)

Max Activating Token Index: 399

Text #5

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.3104. Min Act: -0.0001

Data Index: 1474179 (Python Code)

Max Activating Token Index: 18

Text #6

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.3143. Min Act: -0.0000

Data Index: 1474138 (Python Code)

Max Activating Token Index: 171

Text #7

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.2511. Min Act: -0.0001

Data Index: 1372281 (Python Code)

Max Activating Token Index: 95

Text #8

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.2165. Min Act: -0.0001

Data Index: 1447546 (Python Code)

Max Activating Token Index: 190

Text #9

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.2465. Min Act: -0.0000

Data Index: 1556904 (Python Code)

Max Activating Token Index: 324

Text #10

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.1808. Min Act: -0.0000

Data Index: 1560315 (Python Code)

Max Activating Token Index: 321

Text #11

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.2097. Min Act: -0.0000

Data Index: 1476619 (Python Code)

Max Activating Token Index: 49

Text #12

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.1386. Min Act: -0.0001

Data Index: 1445012 (Python Code)

Max Activating Token Index: 1012

Text #13

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.2345. Min Act: -0.0000

Data Index: 1612987 (Python Code)

Max Activating Token Index: 940

Text #14

Max Range: 1.8973. Min Range: -1.8973

Max Act: 0.9960. Min Act: -0.0000

Data Index: 1432304 (Python Code)

Max Activating Token Index: 102

Text #15

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.0735. Min Act: -0.0000

Data Index: 1612772 (Python Code)

Max Activating Token Index: 387

Text #16

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.1507. Min Act: -0.0000

Data Index: 1539441 (Python Code)

Max Activating Token Index: 247

Text #17

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.0534. Min Act: -0.0000

Data Index: 1641692 (Python Code)

Max Activating Token Index: 297

Text #18

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.0500. Min Act: -0.0000

Data Index: 1641609 (Python Code)

Max Activating Token Index: 564

Text #19

Max Range: 1.8973. Min Range: -1.8973

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1380798 (Python Code)

Max Activating Token Index: 110