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

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

Neuron 2606 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: 0.9306. Min Range: -0.9306

Max Act: 0.9150. Min Act: 0.0000

Data Index: 1506330 (Python Code)

Max Activating Token Index: 81

Text #1

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.9306. Min Act: 0.0000

Data Index: 1609866 (Python Code)

Max Activating Token Index: 190

Text #2

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7593. Min Act: 0.0000

Data Index: 1565908 (Python Code)

Max Activating Token Index: 79

Text #3

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.6445. Min Act: 0.0000

Data Index: 1363459 (Python Code)

Max Activating Token Index: 56

Text #4

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.6244. Min Act: 0.0000

Data Index: 1631119 (Python Code)

Max Activating Token Index: 146

Text #5

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.6148. Min Act: 0.0000

Data Index: 1376197 (Python Code)

Max Activating Token Index: 31

Text #6

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5816. Min Act: 0.0000

Data Index: 1553781 (Python Code)

Max Activating Token Index: 136

Text #7

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.6308. Min Act: 0.0000

Data Index: 1393852 (Python Code)

Max Activating Token Index: 193

Text #8

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5772. Min Act: 0.0000

Data Index: 1627499 (Python Code)

Max Activating Token Index: 33

Text #9

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5875. Min Act: 0.0000

Data Index: 1643024 (Python Code)

Max Activating Token Index: 74

Text #10

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5527. Min Act: 0.0000

Data Index: 1376376 (Python Code)

Max Activating Token Index: 400

Text #11

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.4979. Min Act: 0.0000

Data Index: 1426112 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.4909. Min Act: 0.0000

Data Index: 1400678 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.4881. Min Act: -0.0000

Data Index: 1440188 (Python Code)

Max Activating Token Index: 573

Text #14

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.4966. Min Act: 0.0000

Data Index: 1489303 (Python Code)

Max Activating Token Index: 36

Text #15

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.4577. Min Act: 0.0000

Data Index: 1575003 (Python Code)

Max Activating Token Index: 154

Text #16

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1477643 (Python Code)

Max Activating Token Index: 36

Text #17

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.4220. Min Act: 0.0000

Data Index: 1408063 (Python Code)

Max Activating Token Index: 441

Text #18

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.4383. Min Act: 0.0000

Data Index: 1400426 (Python Code)

Max Activating Token Index: 47

Text #19

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.4213. Min Act: 0.0000

Data Index: 1632680 (Python Code)

Max Activating Token Index: 162