Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1469 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2643. Min Act: -0.0001

Data Index: 725502 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2299. Min Act: -0.0001

Data Index: 1135343 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2371. Min Act: -0.0001

Data Index: 217180 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2247. Min Act: -0.0001

Data Index: 1174959 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2251. Min Act: -0.0001

Data Index: 291547 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2210. Min Act: -0.0001

Data Index: 1014986 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2045. Min Act: -0.0001

Data Index: 1119717 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2097. Min Act: -0.0001

Data Index: 206933 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.1974. Min Act: -0.0001

Data Index: 783207 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.1949. Min Act: -0.0001

Data Index: 136473 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.1928. Min Act: -0.0001

Data Index: 1138051 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.1944. Min Act: -0.0001

Data Index: 1350733 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.1864. Min Act: -0.0001

Data Index: 132619 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.1865. Min Act: -0.0001

Data Index: 262930 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.1824. Min Act: -0.0001

Data Index: 875213 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.1964. Min Act: -0.0001

Data Index: 969356 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.1931. Min Act: -0.0001

Data Index: 1358208 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.1852. Min Act: -0.0001

Data Index: 790745 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.1768. Min Act: -0.0001

Data Index: 1221842 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.1750. Min Act: -0.0001

Data Index: 368713 (C4 (Web Text))

Max Activating Token Index: 641