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

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

Neuron 1993 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.7424. Min Act: -0.0000

Data Index: 326015 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.2274. Min Act: -0.0001

Data Index: 545333 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.2294. Min Act: -0.0000

Data Index: 566370 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.0699. Min Act: -0.0000

Data Index: 313255 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.0216. Min Act: -0.0000

Data Index: 1340872 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.0360. Min Act: -0.0000

Data Index: 1309078 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 1.7424. Min Range: -1.7424

Max Act: 0.9602. Min Act: -0.0000

Data Index: 1179681 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 1.7424. Min Range: -1.7424

Max Act: 0.7870. Min Act: -0.0000

Data Index: 1086588 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 1.7424. Min Range: -1.7424

Max Act: 0.9346. Min Act: -0.0000

Data Index: 652206 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 1.7424. Min Range: -1.7424

Max Act: 0.9336. Min Act: -0.0000

Data Index: 1310144 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 1.7424. Min Range: -1.7424

Max Act: 0.9293. Min Act: -0.0000

Data Index: 170943 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 1.7424. Min Range: -1.7424

Max Act: 0.8805. Min Act: -0.0001

Data Index: 785087 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 1.7424. Min Range: -1.7424

Max Act: 0.8796. Min Act: -0.0000

Data Index: 140635 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 1.7424. Min Range: -1.7424

Max Act: 0.8345. Min Act: -0.0000

Data Index: 1097756 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 1.7424. Min Range: -1.7424

Max Act: 0.8927. Min Act: -0.0000

Data Index: 80698 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 1.7424. Min Range: -1.7424

Max Act: 0.7860. Min Act: -0.0000

Data Index: 331440 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 1.7424. Min Range: -1.7424

Max Act: 0.8430. Min Act: -0.0000

Data Index: 723061 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 1.7424. Min Range: -1.7424

Max Act: 0.8252. Min Act: -0.0000

Data Index: 28751 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 1.7424. Min Range: -1.7424

Max Act: 0.9506. Min Act: -0.0000

Data Index: 870329 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 1.7424. Min Range: -1.7424

Max Act: 0.7894. Min Act: -0.0000

Data Index: 280928 (C4 (Web Text))

Max Activating Token Index: 419