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

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

Neuron 3440 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: 2.0813. Min Range: -2.0813

Max Act: 2.0813. Min Act: -0.0000

Data Index: 1630387 (Python Code)

Max Activating Token Index: 139

Text #1

Max Range: 2.0813. Min Range: -2.0813

Max Act: 1.9638. Min Act: -0.0000

Data Index: 1376959 (Python Code)

Max Activating Token Index: 824

Text #2

Max Range: 2.0813. Min Range: -2.0813

Max Act: 1.4428. Min Act: -0.0000

Data Index: 1641062 (Python Code)

Max Activating Token Index: 235

Text #3

Max Range: 2.0813. Min Range: -2.0813

Max Act: 1.4505. Min Act: -0.0000

Data Index: 1456222 (Python Code)

Max Activating Token Index: 119

Text #4

Max Range: 2.0813. Min Range: -2.0813

Max Act: 1.4449. Min Act: -0.0000

Data Index: 1563095 (Python Code)

Max Activating Token Index: 141

Text #5

Max Range: 2.0813. Min Range: -2.0813

Max Act: 1.2938. Min Act: -0.0000

Data Index: 1405938 (Python Code)

Max Activating Token Index: 82

Text #6

Max Range: 2.0813. Min Range: -2.0813

Max Act: 1.3034. Min Act: -0.0000

Data Index: 1469578 (Python Code)

Max Activating Token Index: 470

Text #7

Max Range: 2.0813. Min Range: -2.0813

Max Act: 1.2748. Min Act: -0.0000

Data Index: 1362589 (Python Code)

Max Activating Token Index: 256

Text #8

Max Range: 2.0813. Min Range: -2.0813

Max Act: 1.2006. Min Act: -0.0000

Data Index: 1572057 (Python Code)

Max Activating Token Index: 688

Text #9

Max Range: 2.0813. Min Range: -2.0813

Max Act: 1.1603. Min Act: -0.0000

Data Index: 1389261 (Python Code)

Max Activating Token Index: 123

Text #10

Max Range: 2.0813. Min Range: -2.0813

Max Act: 1.1471. Min Act: -0.0000

Data Index: 1474323 (Python Code)

Max Activating Token Index: 416

Text #11

Max Range: 2.0813. Min Range: -2.0813

Max Act: 1.1402. Min Act: -0.0000

Data Index: 1579819 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 2.0813. Min Range: -2.0813

Max Act: 1.1299. Min Act: -0.0000

Data Index: 1581948 (Python Code)

Max Activating Token Index: 141

Text #13

Max Range: 2.0813. Min Range: -2.0813

Max Act: 1.1306. Min Act: -0.0000

Data Index: 1387656 (Python Code)

Max Activating Token Index: 47

Text #14

Max Range: 2.0813. Min Range: -2.0813

Max Act: 1.1125. Min Act: -0.0000

Data Index: 1408606 (Python Code)

Max Activating Token Index: 100

Text #15

Max Range: 2.0813. Min Range: -2.0813

Max Act: 1.1202. Min Act: -0.0000

Data Index: 1502150 (Python Code)

Max Activating Token Index: 132

Text #16

Max Range: 2.0813. Min Range: -2.0813

Max Act: 1.0475. Min Act: -0.0000

Data Index: 1562902 (Python Code)

Max Activating Token Index: 138

Text #17

Max Range: 2.0813. Min Range: -2.0813

Max Act: 0.9710. Min Act: -0.0000

Data Index: 1569864 (Python Code)

Max Activating Token Index: 562

Text #18

Max Range: 2.0813. Min Range: -2.0813

Max Act: 1.0079. Min Act: -0.0000

Data Index: 1503088 (Python Code)

Max Activating Token Index: 550

Text #19

Max Range: 2.0813. Min Range: -2.0813

Max Act: 1.0389. Min Act: -0.0000

Data Index: 1510014 (Python Code)

Max Activating Token Index: 858