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

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

Neuron 4717 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: 0.1711. Min Range: -0.1711

Max Act: 0.1697. Min Act: -0.0000

Data Index: 1362804 (Python Code)

Max Activating Token Index: 175

Text #1

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1711. Min Act: -0.0000

Data Index: 1397427 (Python Code)

Max Activating Token Index: 46

Text #2

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1639. Min Act: -0.0000

Data Index: 1532344 (Python Code)

Max Activating Token Index: 171

Text #3

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1624. Min Act: -0.0000

Data Index: 1420867 (Python Code)

Max Activating Token Index: 350

Text #4

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1636. Min Act: -0.0000

Data Index: 1643721 (Python Code)

Max Activating Token Index: 453

Text #5

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1481. Min Act: -0.0000

Data Index: 1452777 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1461. Min Act: -0.0000

Data Index: 1448715 (Python Code)

Max Activating Token Index: 420

Text #7

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1273. Min Act: -0.0000

Data Index: 1626186 (Python Code)

Max Activating Token Index: 845

Text #8

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1225. Min Act: -0.0000

Data Index: 1432789 (Python Code)

Max Activating Token Index: 366

Text #9

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1623658 (Python Code)

Max Activating Token Index: 991

Text #10

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1258. Min Act: -0.0000

Data Index: 112733 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1253. Min Act: -0.0000

Data Index: 1447175 (Python Code)

Max Activating Token Index: 521

Text #12

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1498185 (Python Code)

Max Activating Token Index: 86

Text #13

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1200. Min Act: -0.0000

Data Index: 722262 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1421982 (Python Code)

Max Activating Token Index: 709

Text #15

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1593372 (Python Code)

Max Activating Token Index: 736

Text #16

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1060. Min Act: -0.0000

Data Index: 246793 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1082. Min Act: -0.0000

Data Index: 1483317 (Python Code)

Max Activating Token Index: 177

Text #18

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1490870 (Python Code)

Max Activating Token Index: 495

Text #19

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1606909 (Python Code)

Max Activating Token Index: 693