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

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

Neuron 479 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0260. Min Range: -5.0260

Max Act: 5.0260. Min Act: -0.0000

Data Index: 1593133 (Python Code)

Max Activating Token Index: 127

Text #1

Max Range: 5.0260. Min Range: -5.0260

Max Act: 4.4447. Min Act: -0.0000

Data Index: 1504190 (Python Code)

Max Activating Token Index: 414

Text #2

Max Range: 5.0260. Min Range: -5.0260

Max Act: 4.8146. Min Act: -0.0000

Data Index: 1553749 (Python Code)

Max Activating Token Index: 65

Text #3

Max Range: 5.0260. Min Range: -5.0260

Max Act: 4.8623. Min Act: -0.0000

Data Index: 1467815 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 5.0260. Min Range: -5.0260

Max Act: 4.4295. Min Act: -0.0000

Data Index: 1429627 (Python Code)

Max Activating Token Index: 284

Text #5

Max Range: 5.0260. Min Range: -5.0260

Max Act: 4.0758. Min Act: -0.0000

Data Index: 1568420 (Python Code)

Max Activating Token Index: 713

Text #6

Max Range: 5.0260. Min Range: -5.0260

Max Act: 4.2936. Min Act: -0.0000

Data Index: 1471261 (Python Code)

Max Activating Token Index: 50

Text #7

Max Range: 5.0260. Min Range: -5.0260

Max Act: 4.2522. Min Act: -0.0000

Data Index: 1526000 (Python Code)

Max Activating Token Index: 926

Text #8

Max Range: 5.0260. Min Range: -5.0260

Max Act: 3.9745. Min Act: -0.0000

Data Index: 1417153 (Python Code)

Max Activating Token Index: 915

Text #9

Max Range: 5.0260. Min Range: -5.0260

Max Act: 3.8665. Min Act: -0.0000

Data Index: 1637287 (Python Code)

Max Activating Token Index: 92

Text #10

Max Range: 5.0260. Min Range: -5.0260

Max Act: 4.0392. Min Act: -0.0000

Data Index: 1541389 (Python Code)

Max Activating Token Index: 59

Text #11

Max Range: 5.0260. Min Range: -5.0260

Max Act: 3.6965. Min Act: -0.0000

Data Index: 1463482 (Python Code)

Max Activating Token Index: 987

Text #12

Max Range: 5.0260. Min Range: -5.0260

Max Act: 3.7955. Min Act: -0.0000

Data Index: 1487889 (Python Code)

Max Activating Token Index: 53

Text #13

Max Range: 5.0260. Min Range: -5.0260

Max Act: 3.9291. Min Act: -0.0000

Data Index: 1372400 (Python Code)

Max Activating Token Index: 24

Text #14

Max Range: 5.0260. Min Range: -5.0260

Max Act: 4.0681. Min Act: -0.0000

Data Index: 1465295 (Python Code)

Max Activating Token Index: 29

Text #15

Max Range: 5.0260. Min Range: -5.0260

Max Act: 3.7196. Min Act: -0.0000

Data Index: 1410381 (Python Code)

Max Activating Token Index: 661

Text #16

Max Range: 5.0260. Min Range: -5.0260

Max Act: 3.8427. Min Act: -0.0000

Data Index: 1363653 (Python Code)

Max Activating Token Index: 422

Text #17

Max Range: 5.0260. Min Range: -5.0260

Max Act: 3.6821. Min Act: -0.0000

Data Index: 1626489 (Python Code)

Max Activating Token Index: 979

Text #18

Max Range: 5.0260. Min Range: -5.0260

Max Act: 3.5876. Min Act: -0.0000

Data Index: 1625878 (Python Code)

Max Activating Token Index: 456

Text #19

Max Range: 5.0260. Min Range: -5.0260

Max Act: 3.5832. Min Act: -0.0000

Data Index: 1377003 (Python Code)

Max Activating Token Index: 832