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

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

Neuron 4010 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.8815. Min Act: -0.0000

Data Index: 1151804 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.6863. Min Act: -0.0000

Data Index: 1068381 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.9309. Min Act: -0.0000

Data Index: 1500611 (Python Code)

Max Activating Token Index: 961

Text #3

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.6942. Min Act: -0.0000

Data Index: 1323136 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.5121. Min Act: -0.0000

Data Index: 1491992 (Python Code)

Max Activating Token Index: 353

Text #5

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.6368. Min Act: -0.0000

Data Index: 1423173 (Python Code)

Max Activating Token Index: 193

Text #6

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.4126. Min Act: -0.0000

Data Index: 188441 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.3221. Min Act: -0.0000

Data Index: 15521 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.3282. Min Act: -0.0000

Data Index: 813678 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.6150. Min Act: -0.0000

Data Index: 859713 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.4475. Min Act: -0.0000

Data Index: 545309 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.4286. Min Act: -0.0000

Data Index: 59861 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.3998. Min Act: -0.0000

Data Index: 520401 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.2470. Min Act: -0.0000

Data Index: 1117979 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.3799. Min Act: -0.0000

Data Index: 595555 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.3668. Min Act: -0.0000

Data Index: 969732 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.3447. Min Act: -0.0000

Data Index: 656484 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.3287. Min Act: -0.0000

Data Index: 1159712 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.3242. Min Act: -0.0000

Data Index: 162216 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 3.9309. Min Range: -3.9309

Max Act: 3.2825. Min Act: -0.0000

Data Index: 1255095 (C4 (Web Text))

Max Activating Token Index: 18