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

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

Neuron 5306 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: 0.2603. Min Range: -0.2603

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1596004 (Python Code)

Max Activating Token Index: 176

Text #1

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2498. Min Act: -0.0000

Data Index: 291661 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1554527 (Python Code)

Max Activating Token Index: 820

Text #3

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1513310 (Python Code)

Max Activating Token Index: 700

Text #4

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2260. Min Act: -0.0000

Data Index: 1365890 (Python Code)

Max Activating Token Index: 539

Text #5

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2331. Min Act: -0.0000

Data Index: 232045 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2296. Min Act: -0.0000

Data Index: 326647 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2529. Min Act: -0.0000

Data Index: 955620 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1041273 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1551572 (Python Code)

Max Activating Token Index: 950

Text #10

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2099. Min Act: -0.0000

Data Index: 659242 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2187. Min Act: -0.0000

Data Index: 1415402 (Python Code)

Max Activating Token Index: 392

Text #12

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2058. Min Act: -0.0000

Data Index: 412311 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.1849. Min Act: -0.0000

Data Index: 1649027 (Python Code)

Max Activating Token Index: 775

Text #14

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1585691 (Python Code)

Max Activating Token Index: 183

Text #15

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2030. Min Act: -0.0000

Data Index: 677294 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2044. Min Act: -0.0000

Data Index: 1354542 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.1960. Min Act: -0.0000

Data Index: 1615327 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.1964. Min Act: -0.0000

Data Index: 468179 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.2603. Min Range: -0.2603

Max Act: 0.2353. Min Act: -0.0000

Data Index: 633379 (C4 (Web Text))

Max Activating Token Index: 838