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

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

Neuron 1172 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1888. Min Act: -0.0000

Data Index: 542682 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1671. Min Act: -0.0000

Data Index: 1529651 (Python Code)

Max Activating Token Index: 674

Text #2

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1644. Min Act: -0.0000

Data Index: 1248357 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1553. Min Act: -0.0000

Data Index: 1306714 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1765. Min Act: -0.0000

Data Index: 1521686 (Python Code)

Max Activating Token Index: 1021

Text #5

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1420. Min Act: -0.0000

Data Index: 1112386 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1515. Min Act: -0.0000

Data Index: 479914 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1532619 (Python Code)

Max Activating Token Index: 649

Text #8

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1399. Min Act: -0.0000

Data Index: 709989 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1435. Min Act: -0.0000

Data Index: 498185 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1351. Min Act: -0.0000

Data Index: 908131 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1424216 (Python Code)

Max Activating Token Index: 950

Text #12

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1435. Min Act: -0.0000

Data Index: 301674 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1354. Min Act: -0.0000

Data Index: 988727 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1247. Min Act: -0.0000

Data Index: 757139 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1276. Min Act: -0.0000

Data Index: 1644117 (Python Code)

Max Activating Token Index: 930

Text #16

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1300. Min Act: -0.0000

Data Index: 57133 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1302. Min Act: -0.0000

Data Index: 1149395 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1296. Min Act: -0.0000

Data Index: 1117061 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1414530 (Python Code)

Max Activating Token Index: 837