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

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

Neuron 3773 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1226. Min Act: -0.0001

Data Index: 524413 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1439. Min Act: -0.0001

Data Index: 684640 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1292. Min Act: -0.0000

Data Index: 497632 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1193. Min Act: -0.0001

Data Index: 721650 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1176. Min Act: -0.0001

Data Index: 956667 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1165. Min Act: -0.0001

Data Index: 277435 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1217. Min Act: -0.0001

Data Index: 162491 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1088. Min Act: -0.0001

Data Index: 159635 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1099. Min Act: -0.0001

Data Index: 148508 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1057. Min Act: -0.0001

Data Index: 880356 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1051. Min Act: -0.0001

Data Index: 1350860 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.0959. Min Act: -0.0000

Data Index: 241751 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1317850 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.0979. Min Act: -0.0001

Data Index: 263005 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.0943. Min Act: -0.0001

Data Index: 1127422 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.0913. Min Act: -0.0001

Data Index: 893649 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.0946. Min Act: -0.0001

Data Index: 1070764 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.0995. Min Act: -0.0001

Data Index: 1255183 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.0892. Min Act: -0.0001

Data Index: 301762 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.0933. Min Act: -0.0001

Data Index: 442110 (C4 (Web Text))

Max Activating Token Index: 914