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

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

Neuron 3920 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: 0.1959. Min Range: -0.1959

Max Act: 0.1959. Min Act: -0.0000

Data Index: 1433053 (Python Code)

Max Activating Token Index: 984

Text #1

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1569. Min Act: -0.0000

Data Index: 1476744 (Python Code)

Max Activating Token Index: 1012

Text #2

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1431. Min Act: -0.0000

Data Index: 1027863 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1629952 (Python Code)

Max Activating Token Index: 304

Text #4

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1370. Min Act: -0.0000

Data Index: 1477982 (Python Code)

Max Activating Token Index: 488

Text #5

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1462. Min Act: -0.0000

Data Index: 1364982 (Python Code)

Max Activating Token Index: 849

Text #6

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1361767 (Python Code)

Max Activating Token Index: 676

Text #7

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1311. Min Act: -0.0000

Data Index: 1581442 (Python Code)

Max Activating Token Index: 973

Text #8

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1320. Min Act: -0.0000

Data Index: 1410336 (Python Code)

Max Activating Token Index: 234

Text #9

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1366495 (Python Code)

Max Activating Token Index: 788

Text #10

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1338. Min Act: -0.0000

Data Index: 1372871 (Python Code)

Max Activating Token Index: 899

Text #11

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1582315 (Python Code)

Max Activating Token Index: 676

Text #12

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1261. Min Act: -0.0000

Data Index: 1420110 (Python Code)

Max Activating Token Index: 972

Text #13

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1205. Min Act: -0.0000

Data Index: 1415480 (Python Code)

Max Activating Token Index: 235

Text #14

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1156. Min Act: -0.0000

Data Index: 1419706 (Python Code)

Max Activating Token Index: 614

Text #15

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1129. Min Act: -0.0000

Data Index: 1494261 (Python Code)

Max Activating Token Index: 304

Text #16

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1203. Min Act: -0.0000

Data Index: 1396155 (Python Code)

Max Activating Token Index: 273

Text #17

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1072. Min Act: -0.0000

Data Index: 1424883 (Python Code)

Max Activating Token Index: 936

Text #18

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1204. Min Act: -0.0000

Data Index: 1545444 (Python Code)

Max Activating Token Index: 140

Text #19

Max Range: 0.1959. Min Range: -0.1959

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1360860 (Python Code)

Max Activating Token Index: 432