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

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

Neuron 1142 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2076. Min Range: -4.2076

Max Act: 3.5243. Min Act: -0.0000

Data Index: 1407120 (Python Code)

Max Activating Token Index: 740

Text #1

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.0129. Min Act: -0.0000

Data Index: 1521152 (Python Code)

Max Activating Token Index: 930

Text #2

Max Range: 4.2076. Min Range: -4.2076

Max Act: 3.3984. Min Act: -0.0000

Data Index: 1629239 (Python Code)

Max Activating Token Index: 396

Text #3

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.2076. Min Act: -0.0000

Data Index: 1410888 (Python Code)

Max Activating Token Index: 730

Text #4

Max Range: 4.2076. Min Range: -4.2076

Max Act: 3.0415. Min Act: -0.0000

Data Index: 1569894 (Python Code)

Max Activating Token Index: 954

Text #5

Max Range: 4.2076. Min Range: -4.2076

Max Act: 3.6612. Min Act: -0.0000

Data Index: 1588357 (Python Code)

Max Activating Token Index: 859

Text #6

Max Range: 4.2076. Min Range: -4.2076

Max Act: 3.4479. Min Act: -0.0000

Data Index: 313965 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 4.2076. Min Range: -4.2076

Max Act: 3.5664. Min Act: -0.0000

Data Index: 1644420 (Python Code)

Max Activating Token Index: 760

Text #8

Max Range: 4.2076. Min Range: -4.2076

Max Act: 3.4289. Min Act: -0.0000

Data Index: 1596869 (Python Code)

Max Activating Token Index: 588

Text #9

Max Range: 4.2076. Min Range: -4.2076

Max Act: 3.3977. Min Act: -0.0000

Data Index: 1595138 (Python Code)

Max Activating Token Index: 339

Text #10

Max Range: 4.2076. Min Range: -4.2076

Max Act: 3.5253. Min Act: -0.0000

Data Index: 1532284 (Python Code)

Max Activating Token Index: 840

Text #11

Max Range: 4.2076. Min Range: -4.2076

Max Act: 3.5508. Min Act: -0.0000

Data Index: 1515814 (Python Code)

Max Activating Token Index: 638

Text #12

Max Range: 4.2076. Min Range: -4.2076

Max Act: 3.2226. Min Act: -0.0000

Data Index: 3240 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 4.2076. Min Range: -4.2076

Max Act: 3.3535. Min Act: -0.0000

Data Index: 1580986 (Python Code)

Max Activating Token Index: 931

Text #14

Max Range: 4.2076. Min Range: -4.2076

Max Act: 3.1773. Min Act: -0.0000

Data Index: 1600510 (Python Code)

Max Activating Token Index: 322

Text #15

Max Range: 4.2076. Min Range: -4.2076

Max Act: 3.4220. Min Act: -0.0000

Data Index: 1534599 (Python Code)

Max Activating Token Index: 327

Text #16

Max Range: 4.2076. Min Range: -4.2076

Max Act: 3.4603. Min Act: -0.0000

Data Index: 1515211 (Python Code)

Max Activating Token Index: 663

Text #17

Max Range: 4.2076. Min Range: -4.2076

Max Act: 3.1439. Min Act: -0.0000

Data Index: 1543704 (Python Code)

Max Activating Token Index: 307

Text #18

Max Range: 4.2076. Min Range: -4.2076

Max Act: 3.4217. Min Act: -0.0000

Data Index: 1421816 (Python Code)

Max Activating Token Index: 954

Text #19

Max Range: 4.2076. Min Range: -4.2076

Max Act: 3.3909. Min Act: -0.0000

Data Index: 1642859 (Python Code)

Max Activating Token Index: 832