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

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

Neuron 3468 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: 0.1969. Min Range: -0.1969

Max Act: 0.1969. Min Act: -0.0001

Data Index: 1653347 (Python Code)

Max Activating Token Index: 401

Text #1

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1820. Min Act: -0.0001

Data Index: 1628880 (Python Code)

Max Activating Token Index: 592

Text #2

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1859. Min Act: -0.0001

Data Index: 735378 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1629. Min Act: -0.0001

Data Index: 1430223 (Python Code)

Max Activating Token Index: 752

Text #4

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1614603 (Python Code)

Max Activating Token Index: 732

Text #5

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1422. Min Act: -0.0001

Data Index: 1274045 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1048146 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1344. Min Act: -0.0001

Data Index: 1450097 (Python Code)

Max Activating Token Index: 779

Text #8

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1354. Min Act: -0.0001

Data Index: 1653936 (Python Code)

Max Activating Token Index: 70

Text #9

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1414. Min Act: -0.0001

Data Index: 1591195 (Python Code)

Max Activating Token Index: 620

Text #10

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1558233 (Python Code)

Max Activating Token Index: 533

Text #11

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1328. Min Act: -0.0001

Data Index: 1567820 (Python Code)

Max Activating Token Index: 82

Text #12

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1290. Min Act: -0.0001

Data Index: 1485622 (Python Code)

Max Activating Token Index: 814

Text #13

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1286. Min Act: -0.0001

Data Index: 1485115 (Python Code)

Max Activating Token Index: 56

Text #14

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1277. Min Act: -0.0001

Data Index: 1575243 (Python Code)

Max Activating Token Index: 104

Text #15

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1264. Min Act: -0.0001

Data Index: 1553107 (Python Code)

Max Activating Token Index: 167

Text #16

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1490596 (Python Code)

Max Activating Token Index: 746

Text #17

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1305. Min Act: -0.0001

Data Index: 1618852 (Python Code)

Max Activating Token Index: 55

Text #18

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1195. Min Act: -0.0001

Data Index: 1413269 (Python Code)

Max Activating Token Index: 575

Text #19

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1386526 (Python Code)

Max Activating Token Index: 331