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

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

Neuron 928 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.3352. Min Act: 0.0000

Data Index: 1085302 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.3218. Min Act: 0.0000

Data Index: 1279131 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.3043. Min Act: -0.0000

Data Index: 52629 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2884. Min Act: -0.0000

Data Index: 1330069 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2794. Min Act: -0.0000

Data Index: 694589 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2765. Min Act: -0.0000

Data Index: 1139734 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2257. Min Act: 0.0000

Data Index: 1212878 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2376. Min Act: -0.0000

Data Index: 558839 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2484. Min Act: -0.0000

Data Index: 366898 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2389. Min Act: -0.0000

Data Index: 298678 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2243. Min Act: 0.0000

Data Index: 1325153 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1217901 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2026. Min Act: -0.0000

Data Index: 1332380 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2043. Min Act: -0.0000

Data Index: 837570 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2050. Min Act: 0.0000

Data Index: 320666 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2148. Min Act: -0.0000

Data Index: 883821 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2080. Min Act: 0.0000

Data Index: 784269 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.1936. Min Act: -0.0000

Data Index: 136271 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.1905. Min Act: -0.0000

Data Index: 707312 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.1798. Min Act: 0.0000

Data Index: 616202 (C4 (Web Text))

Max Activating Token Index: 196