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

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

Neuron 1459 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1549004 (Python Code)

Max Activating Token Index: 81

Text #1

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1511. Min Act: -0.0000

Data Index: 1576434 (Python Code)

Max Activating Token Index: 761

Text #2

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1638326 (Python Code)

Max Activating Token Index: 68

Text #3

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1424770 (Python Code)

Max Activating Token Index: 150

Text #4

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1287. Min Act: -0.0000

Data Index: 1505054 (Python Code)

Max Activating Token Index: 947

Text #5

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1322. Min Act: -0.0000

Data Index: 1600527 (Python Code)

Max Activating Token Index: 552

Text #6

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1317. Min Act: -0.0000

Data Index: 1488886 (Python Code)

Max Activating Token Index: 1013

Text #7

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1222. Min Act: -0.0000

Data Index: 1546214 (Python Code)

Max Activating Token Index: 1007

Text #8

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1230. Min Act: -0.0000

Data Index: 1655423 (Python Code)

Max Activating Token Index: 665

Text #9

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1217. Min Act: -0.0000

Data Index: 1516082 (Python Code)

Max Activating Token Index: 509

Text #10

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1565982 (Python Code)

Max Activating Token Index: 892

Text #11

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1177. Min Act: -0.0000

Data Index: 470579 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1095. Min Act: -0.0000

Data Index: 1450702 (Python Code)

Max Activating Token Index: 268

Text #13

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.0967. Min Act: -0.0000

Data Index: 1420622 (Python Code)

Max Activating Token Index: 879

Text #14

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1511667 (Python Code)

Max Activating Token Index: 314

Text #15

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1578311 (Python Code)

Max Activating Token Index: 284

Text #16

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1045. Min Act: -0.0000

Data Index: 1548384 (Python Code)

Max Activating Token Index: 592

Text #17

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1089. Min Act: -0.0000

Data Index: 1508326 (Python Code)

Max Activating Token Index: 658

Text #18

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1216250 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1497761 (Python Code)

Max Activating Token Index: 994