Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2392 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0402. Min Act: -0.0004

Data Index: 1632062 (Python Code)

Max Activating Token Index: 150

Text #1

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0332. Min Act: -0.0004

Data Index: 1440714 (Python Code)

Max Activating Token Index: 925

Text #2

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0345. Min Act: -0.0004

Data Index: 1420019 (Python Code)

Max Activating Token Index: 84

Text #3

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0351. Min Act: -0.0004

Data Index: 1456569 (Python Code)

Max Activating Token Index: 231

Text #4

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0346. Min Act: -0.0004

Data Index: 1598727 (Python Code)

Max Activating Token Index: 922

Text #5

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0333. Min Act: -0.0004

Data Index: 1654079 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0340. Min Act: -0.0004

Data Index: 1553779 (Python Code)

Max Activating Token Index: 461

Text #7

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0349. Min Act: -0.0004

Data Index: 1652466 (Python Code)

Max Activating Token Index: 563

Text #8

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0361. Min Act: -0.0004

Data Index: 1520177 (Python Code)

Max Activating Token Index: 225

Text #9

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0320. Min Act: -0.0004

Data Index: 1645871 (Python Code)

Max Activating Token Index: 143

Text #10

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0293. Min Act: -0.0004

Data Index: 1551315 (Python Code)

Max Activating Token Index: 886

Text #11

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0323. Min Act: -0.0004

Data Index: 1582167 (Python Code)

Max Activating Token Index: 555

Text #12

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0312. Min Act: -0.0004

Data Index: 1550827 (Python Code)

Max Activating Token Index: 772

Text #13

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0316. Min Act: -0.0004

Data Index: 1535250 (Python Code)

Max Activating Token Index: 594

Text #14

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0322. Min Act: -0.0004

Data Index: 1585070 (Python Code)

Max Activating Token Index: 543

Text #15

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0340. Min Act: -0.0004

Data Index: 1488385 (Python Code)

Max Activating Token Index: 799

Text #16

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0321. Min Act: -0.0004

Data Index: 1583259 (Python Code)

Max Activating Token Index: 58

Text #17

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0326. Min Act: -0.0004

Data Index: 1416521 (Python Code)

Max Activating Token Index: 59

Text #18

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0322. Min Act: -0.0004

Data Index: 1503758 (Python Code)

Max Activating Token Index: 215

Text #19

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0324. Min Act: -0.0004

Data Index: 1587544 (Python Code)

Max Activating Token Index: 80