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

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

Neuron 2716 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2475. Min Act: -0.0001

Data Index: 1530365 (Python Code)

Max Activating Token Index: 256

Text #1

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2324. Min Act: -0.0001

Data Index: 1616847 (Python Code)

Max Activating Token Index: 312

Text #2

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2181. Min Act: -0.0001

Data Index: 1465762 (Python Code)

Max Activating Token Index: 196

Text #3

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1965. Min Act: -0.0001

Data Index: 1617118 (Python Code)

Max Activating Token Index: 986

Text #4

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2113. Min Act: -0.0001

Data Index: 1519719 (Python Code)

Max Activating Token Index: 305

Text #5

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2198. Min Act: -0.0001

Data Index: 1401595 (Python Code)

Max Activating Token Index: 676

Text #6

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1679. Min Act: -0.0001

Data Index: 1535859 (Python Code)

Max Activating Token Index: 253

Text #7

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1860. Min Act: -0.0001

Data Index: 1528098 (Python Code)

Max Activating Token Index: 434

Text #8

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1648. Min Act: -0.0001

Data Index: 90670 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1769. Min Act: -0.0001

Data Index: 1055810 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1644. Min Act: -0.0001

Data Index: 1590533 (Python Code)

Max Activating Token Index: 932

Text #11

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1635. Min Act: -0.0001

Data Index: 1341681 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1619. Min Act: -0.0001

Data Index: 1157481 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1600. Min Act: -0.0001

Data Index: 173891 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1708. Min Act: -0.0001

Data Index: 1415973 (Python Code)

Max Activating Token Index: 189

Text #15

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1690. Min Act: -0.0001

Data Index: 1318220 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1636. Min Act: -0.0001

Data Index: 1343463 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1339589 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1421. Min Act: -0.0001

Data Index: 1465810 (Python Code)

Max Activating Token Index: 178

Text #19

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1633. Min Act: -0.0001

Data Index: 275314 (C4 (Web Text))

Max Activating Token Index: 623