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

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

Neuron 4791 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.7706. Min Act: -0.0000

Data Index: 1206220 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.7236. Min Act: -0.0000

Data Index: 1370271 (Python Code)

Max Activating Token Index: 331

Text #2

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.4807. Min Act: -0.0000

Data Index: 252585 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.5060. Min Act: -0.0000

Data Index: 798595 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.5077. Min Act: -0.0000

Data Index: 337480 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.4378. Min Act: -0.0000

Data Index: 470658 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.3963. Min Act: -0.0000

Data Index: 19995 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.3352. Min Act: -0.0000

Data Index: 426707 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.3139. Min Act: -0.0000

Data Index: 613123 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.3133. Min Act: -0.0000

Data Index: 547375 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.2925. Min Act: -0.0000

Data Index: 455686 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.3194. Min Act: -0.0000

Data Index: 447915 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.2823. Min Act: -0.0000

Data Index: 1527573 (Python Code)

Max Activating Token Index: 54

Text #13

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.2217. Min Act: -0.0000

Data Index: 443947 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.2993. Min Act: -0.0000

Data Index: 914656 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.2590. Min Act: -0.0000

Data Index: 951149 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.2424. Min Act: -0.0000

Data Index: 1121193 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.2410. Min Act: -0.0000

Data Index: 105226 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.2077. Min Act: -0.0000

Data Index: 230128 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 1.7706. Min Range: -1.7706

Max Act: 1.2372. Min Act: -0.0000

Data Index: 513965 (C4 (Web Text))

Max Activating Token Index: 15