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

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

Neuron 5752 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: 2.3077. Min Range: -2.3077

Max Act: 2.3077. Min Act: -0.0000

Data Index: 1639050 (Python Code)

Max Activating Token Index: 596

Text #1

Max Range: 2.3077. Min Range: -2.3077

Max Act: 2.2451. Min Act: -0.0000

Data Index: 825916 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 2.3077. Min Range: -2.3077

Max Act: 2.2236. Min Act: -0.0000

Data Index: 1512973 (Python Code)

Max Activating Token Index: 39

Text #3

Max Range: 2.3077. Min Range: -2.3077

Max Act: 1.8962. Min Act: -0.0000

Data Index: 1610599 (Python Code)

Max Activating Token Index: 419

Text #4

Max Range: 2.3077. Min Range: -2.3077

Max Act: 1.9975. Min Act: -0.0000

Data Index: 1402100 (Python Code)

Max Activating Token Index: 961

Text #5

Max Range: 2.3077. Min Range: -2.3077

Max Act: 1.9182. Min Act: -0.0000

Data Index: 1596106 (Python Code)

Max Activating Token Index: 781

Text #6

Max Range: 2.3077. Min Range: -2.3077

Max Act: 1.6923. Min Act: -0.0000

Data Index: 1005386 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 2.3077. Min Range: -2.3077

Max Act: 1.7845. Min Act: -0.0000

Data Index: 1594044 (Python Code)

Max Activating Token Index: 738

Text #8

Max Range: 2.3077. Min Range: -2.3077

Max Act: 1.7270. Min Act: -0.0000

Data Index: 1529752 (Python Code)

Max Activating Token Index: 712

Text #9

Max Range: 2.3077. Min Range: -2.3077

Max Act: 1.8006. Min Act: -0.0000

Data Index: 329615 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 2.3077. Min Range: -2.3077

Max Act: 1.6571. Min Act: -0.0000

Data Index: 1107992 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 2.3077. Min Range: -2.3077

Max Act: 1.7196. Min Act: -0.0000

Data Index: 248095 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 2.3077. Min Range: -2.3077

Max Act: 1.5172. Min Act: -0.0000

Data Index: 1551059 (Python Code)

Max Activating Token Index: 331

Text #13

Max Range: 2.3077. Min Range: -2.3077

Max Act: 1.5455. Min Act: -0.0000

Data Index: 17948 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 2.3077. Min Range: -2.3077

Max Act: 1.4760. Min Act: -0.0000

Data Index: 1506429 (Python Code)

Max Activating Token Index: 974

Text #15

Max Range: 2.3077. Min Range: -2.3077

Max Act: 1.5523. Min Act: -0.0000

Data Index: 1363051 (Python Code)

Max Activating Token Index: 33

Text #16

Max Range: 2.3077. Min Range: -2.3077

Max Act: 1.6323. Min Act: -0.0000

Data Index: 243967 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 2.3077. Min Range: -2.3077

Max Act: 1.5387. Min Act: -0.0000

Data Index: 1385275 (Python Code)

Max Activating Token Index: 314

Text #18

Max Range: 2.3077. Min Range: -2.3077

Max Act: 1.6916. Min Act: -0.0000

Data Index: 1382253 (Python Code)

Max Activating Token Index: 319

Text #19

Max Range: 2.3077. Min Range: -2.3077

Max Act: 1.5881. Min Act: -0.0000

Data Index: 893922 (C4 (Web Text))

Max Activating Token Index: 196