Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1981 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 6.5292. Min Range: -6.5292

Max Act: 6.5292. Min Act: -0.0000

Data Index: 896715 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 6.5292. Min Range: -6.5292

Max Act: 5.9831. Min Act: -0.0000

Data Index: 930935 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 6.5292. Min Range: -6.5292

Max Act: 5.7583. Min Act: -0.0000

Data Index: 580988 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 6.5292. Min Range: -6.5292

Max Act: 5.8088. Min Act: -0.0000

Data Index: 966265 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 6.5292. Min Range: -6.5292

Max Act: 5.2214. Min Act: 0.0000

Data Index: 1125162 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 6.5292. Min Range: -6.5292

Max Act: 5.4269. Min Act: -0.0000

Data Index: 1112186 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 6.5292. Min Range: -6.5292

Max Act: 5.1921. Min Act: -0.0000

Data Index: 1225508 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 6.5292. Min Range: -6.5292

Max Act: 5.2223. Min Act: -0.0000

Data Index: 1277105 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 6.5292. Min Range: -6.5292

Max Act: 4.8418. Min Act: -0.0000

Data Index: 345527 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 6.5292. Min Range: -6.5292

Max Act: 5.1054. Min Act: -0.0000

Data Index: 379782 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 6.5292. Min Range: -6.5292

Max Act: 4.9736. Min Act: -0.0000

Data Index: 956545 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 6.5292. Min Range: -6.5292

Max Act: 5.0915. Min Act: -0.0000

Data Index: 207064 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 6.5292. Min Range: -6.5292

Max Act: 5.2514. Min Act: -0.0000

Data Index: 1375381 (Python Code)

Max Activating Token Index: 618

Text #13

Max Range: 6.5292. Min Range: -6.5292

Max Act: 4.5169. Min Act: -0.0000

Data Index: 263511 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 6.5292. Min Range: -6.5292

Max Act: 5.0625. Min Act: -0.0000

Data Index: 79948 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 6.5292. Min Range: -6.5292

Max Act: 4.8177. Min Act: -0.0000

Data Index: 1130630 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 6.5292. Min Range: -6.5292

Max Act: 4.7522. Min Act: -0.0000

Data Index: 520933 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 6.5292. Min Range: -6.5292

Max Act: 4.7399. Min Act: -0.0000

Data Index: 197114 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 6.5292. Min Range: -6.5292

Max Act: 4.9996. Min Act: -0.0000

Data Index: 1127793 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 6.5292. Min Range: -6.5292

Max Act: 4.5840. Min Act: -0.0000

Data Index: 623184 (C4 (Web Text))

Max Activating Token Index: 719