Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 520 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.2224. Min Act: -0.0002

Data Index: 283313 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.2296. Min Act: -0.0002

Data Index: 1140077 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.2214. Min Act: -0.0002

Data Index: 1153567 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.2152. Min Act: -0.0001

Data Index: 764566 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.2195. Min Act: -0.0002

Data Index: 143236 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1941. Min Act: -0.0001

Data Index: 1055407 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1847. Min Act: -0.0002

Data Index: 405917 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.2006. Min Act: -0.0002

Data Index: 686799 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.2007. Min Act: -0.0002

Data Index: 1181288 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1899. Min Act: -0.0002

Data Index: 85644 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1907. Min Act: -0.0002

Data Index: 797596 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1854. Min Act: -0.0002

Data Index: 1261725 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1917. Min Act: -0.0002

Data Index: 816269 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1854. Min Act: -0.0002

Data Index: 916488 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1939. Min Act: -0.0002

Data Index: 350388 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1833. Min Act: -0.0002

Data Index: 915484 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1791. Min Act: -0.0002

Data Index: 1320892 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1800. Min Act: -0.0002

Data Index: 477651 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1857. Min Act: -0.0002

Data Index: 771245 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1824. Min Act: -0.0002

Data Index: 1333307 (C4 (Web Text))

Max Activating Token Index: 929