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

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

Neuron 2495 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2975. Min Act: -0.0000

Data Index: 650196 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2936. Min Act: -0.0000

Data Index: 603926 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2735. Min Act: -0.0000

Data Index: 165856 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2800. Min Act: -0.0000

Data Index: 376969 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2539. Min Act: -0.0000

Data Index: 712988 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1016005 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2306. Min Act: -0.0000

Data Index: 804043 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2056. Min Act: -0.0000

Data Index: 618400 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2234. Min Act: -0.0000

Data Index: 704351 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1253139 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2456. Min Act: -0.0000

Data Index: 1515115 (Python Code)

Max Activating Token Index: 383

Text #11

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2171. Min Act: -0.0000

Data Index: 1066040 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1049061 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2001. Min Act: -0.0000

Data Index: 191390 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.1830. Min Act: -0.0000

Data Index: 1629428 (Python Code)

Max Activating Token Index: 882

Text #15

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1437532 (Python Code)

Max Activating Token Index: 537

Text #16

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.1812. Min Act: -0.0000

Data Index: 544906 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1585317 (Python Code)

Max Activating Token Index: 862

Text #18

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2071. Min Act: -0.0000

Data Index: 867635 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.1983. Min Act: -0.0000

Data Index: 369239 (C4 (Web Text))

Max Activating Token Index: 657