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

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

Neuron 70 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1228. Min Range: -2.1228

Max Act: 2.1228. Min Act: -0.0000

Data Index: 601486 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 2.1228. Min Range: -2.1228

Max Act: 1.8714. Min Act: -0.0000

Data Index: 241361 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 2.1228. Min Range: -2.1228

Max Act: 1.7550. Min Act: -0.0000

Data Index: 999936 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 2.1228. Min Range: -2.1228

Max Act: 1.7822. Min Act: -0.0000

Data Index: 601257 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 2.1228. Min Range: -2.1228

Max Act: 1.6296. Min Act: -0.0000

Data Index: 1214716 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 2.1228. Min Range: -2.1228

Max Act: 1.7245. Min Act: -0.0000

Data Index: 1655490 (Python Code)

Max Activating Token Index: 354

Text #6

Max Range: 2.1228. Min Range: -2.1228

Max Act: 1.8136. Min Act: -0.0000

Data Index: 1137458 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 2.1228. Min Range: -2.1228

Max Act: 1.6571. Min Act: -0.0000

Data Index: 1202322 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 2.1228. Min Range: -2.1228

Max Act: 1.6579. Min Act: -0.0000

Data Index: 78930 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 2.1228. Min Range: -2.1228

Max Act: 1.6089. Min Act: -0.0000

Data Index: 487917 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 2.1228. Min Range: -2.1228

Max Act: 1.6102. Min Act: -0.0000

Data Index: 503860 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 2.1228. Min Range: -2.1228

Max Act: 1.5917. Min Act: -0.0000

Data Index: 595689 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 2.1228. Min Range: -2.1228

Max Act: 1.5335. Min Act: -0.0000

Data Index: 1348939 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 2.1228. Min Range: -2.1228

Max Act: 1.6419. Min Act: -0.0000

Data Index: 299536 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 2.1228. Min Range: -2.1228

Max Act: 1.5201. Min Act: -0.0000

Data Index: 433935 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 2.1228. Min Range: -2.1228

Max Act: 1.5068. Min Act: -0.0000

Data Index: 908615 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 2.1228. Min Range: -2.1228

Max Act: 1.4761. Min Act: -0.0000

Data Index: 731485 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 2.1228. Min Range: -2.1228

Max Act: 1.4739. Min Act: -0.0000

Data Index: 449977 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 2.1228. Min Range: -2.1228

Max Act: 1.5135. Min Act: -0.0000

Data Index: 431902 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 2.1228. Min Range: -2.1228

Max Act: 1.4793. Min Act: -0.0000

Data Index: 543194 (C4 (Web Text))

Max Activating Token Index: 277