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

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

Neuron 67 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: 0.2293. Min Range: -0.2293

Max Act: 0.2293. Min Act: -0.0000

Data Index: 1507 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2282. Min Act: -0.0000

Data Index: 875054 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2062. Min Act: -0.0000

Data Index: 592957 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2088. Min Act: -0.0000

Data Index: 203466 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2166. Min Act: -0.0000

Data Index: 306461 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1188720 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2080. Min Act: -0.0000

Data Index: 116723 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1987. Min Act: -0.0000

Data Index: 104447 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1897. Min Act: -0.0000

Data Index: 802145 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1187708 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1985. Min Act: -0.0000

Data Index: 379607 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1946. Min Act: -0.0000

Data Index: 1124587 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1088544 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1849. Min Act: -0.0000

Data Index: 606338 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1843. Min Act: -0.0000

Data Index: 480260 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1764. Min Act: -0.0000

Data Index: 80324 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1829. Min Act: -0.0000

Data Index: 1159775 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1895. Min Act: -0.0000

Data Index: 360640 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1822. Min Act: -0.0000

Data Index: 217219 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1815. Min Act: -0.0000

Data Index: 521411 (C4 (Web Text))

Max Activating Token Index: 513