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

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

Neuron 1506 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: 1.6146. Min Range: -1.6146

Max Act: 1.6146. Min Act: 0.0000

Data Index: 1429975 (Python Code)

Max Activating Token Index: 926

Text #1

Max Range: 1.6146. Min Range: -1.6146

Max Act: 1.5260. Min Act: -0.0000

Data Index: 1587415 (Python Code)

Max Activating Token Index: 857

Text #2

Max Range: 1.6146. Min Range: -1.6146

Max Act: 1.4338. Min Act: -0.0000

Data Index: 1524396 (Python Code)

Max Activating Token Index: 43

Text #3

Max Range: 1.6146. Min Range: -1.6146

Max Act: 1.3865. Min Act: -0.0000

Data Index: 1500887 (Python Code)

Max Activating Token Index: 303

Text #4

Max Range: 1.6146. Min Range: -1.6146

Max Act: 1.4376. Min Act: 0.0000

Data Index: 1614277 (Python Code)

Max Activating Token Index: 1022

Text #5

Max Range: 1.6146. Min Range: -1.6146

Max Act: 1.3382. Min Act: 0.0000

Data Index: 1365954 (Python Code)

Max Activating Token Index: 324

Text #6

Max Range: 1.6146. Min Range: -1.6146

Max Act: 1.3227. Min Act: -0.0000

Data Index: 1517459 (Python Code)

Max Activating Token Index: 313

Text #7

Max Range: 1.6146. Min Range: -1.6146

Max Act: 1.2791. Min Act: -0.0000

Data Index: 1628401 (Python Code)

Max Activating Token Index: 163

Text #8

Max Range: 1.6146. Min Range: -1.6146

Max Act: 1.2842. Min Act: -0.0000

Data Index: 1560197 (Python Code)

Max Activating Token Index: 404

Text #9

Max Range: 1.6146. Min Range: -1.6146

Max Act: 1.2776. Min Act: 0.0000

Data Index: 1612514 (Python Code)

Max Activating Token Index: 599

Text #10

Max Range: 1.6146. Min Range: -1.6146

Max Act: 1.2721. Min Act: -0.0000

Data Index: 1460409 (Python Code)

Max Activating Token Index: 991

Text #11

Max Range: 1.6146. Min Range: -1.6146

Max Act: 1.1903. Min Act: -0.0000

Data Index: 1504444 (Python Code)

Max Activating Token Index: 277

Text #12

Max Range: 1.6146. Min Range: -1.6146

Max Act: 1.2593. Min Act: -0.0000

Data Index: 1458109 (Python Code)

Max Activating Token Index: 206

Text #13

Max Range: 1.6146. Min Range: -1.6146

Max Act: 1.2420. Min Act: -0.0000

Data Index: 1600336 (Python Code)

Max Activating Token Index: 68

Text #14

Max Range: 1.6146. Min Range: -1.6146

Max Act: 1.2299. Min Act: 0.0000

Data Index: 1497644 (Python Code)

Max Activating Token Index: 132

Text #15

Max Range: 1.6146. Min Range: -1.6146

Max Act: 1.2073. Min Act: 0.0000

Data Index: 1437447 (Python Code)

Max Activating Token Index: 821

Text #16

Max Range: 1.6146. Min Range: -1.6146

Max Act: 1.2219. Min Act: 0.0000

Data Index: 1361422 (Python Code)

Max Activating Token Index: 101

Text #17

Max Range: 1.6146. Min Range: -1.6146

Max Act: 1.1993. Min Act: -0.0000

Data Index: 1388149 (Python Code)

Max Activating Token Index: 515

Text #18

Max Range: 1.6146. Min Range: -1.6146

Max Act: 1.2543. Min Act: 0.0000

Data Index: 1485504 (Python Code)

Max Activating Token Index: 623

Text #19

Max Range: 1.6146. Min Range: -1.6146

Max Act: 1.1830. Min Act: 0.0000

Data Index: 1512687 (Python Code)

Max Activating Token Index: 119