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

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

Neuron 6023 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: 0.0884. Min Range: -0.0884

Max Act: 0.0857. Min Act: -0.0001

Data Index: 431441 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0656. Min Act: -0.0001

Data Index: 1405737 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0536. Min Act: -0.0001

Data Index: 1570464 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0884. Min Act: -0.0000

Data Index: 1371544 (Python Code)

Max Activating Token Index: 59

Text #4

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0395. Min Act: -0.0000

Data Index: 1520511 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1551195 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0359. Min Act: -0.0000

Data Index: 1003149 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0476. Min Act: -0.0000

Data Index: 1575070 (Python Code)

Max Activating Token Index: 826

Text #8

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1367441 (Python Code)

Max Activating Token Index: 50

Text #9

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0339. Min Act: -0.0000

Data Index: 1628471 (Python Code)

Max Activating Token Index: 277

Text #10

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0345. Min Act: -0.0001

Data Index: 670423 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0361. Min Act: -0.0001

Data Index: 119192 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0357. Min Act: -0.0000

Data Index: 1562912 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0327. Min Act: -0.0000

Data Index: 1490769 (Python Code)

Max Activating Token Index: 130

Text #14

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0268. Min Act: -0.0000

Data Index: 1388714 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0320. Min Act: -0.0001

Data Index: 419289 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0316. Min Act: -0.0001

Data Index: 1655684 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1180534 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0383. Min Act: -0.0000

Data Index: 1364130 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0321. Min Act: -0.0000

Data Index: 178251 (C4 (Web Text))

Max Activating Token Index: 308