Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2965 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1419. Min Act: -0.0002

Data Index: 217303 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1366. Min Act: -0.0001

Data Index: 451399 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1140061 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1209. Min Act: -0.0001

Data Index: 470168 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1248. Min Act: -0.0001

Data Index: 870777 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1305. Min Act: -0.0002

Data Index: 1121045 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1164. Min Act: -0.0001

Data Index: 631099 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1218. Min Act: -0.0001

Data Index: 471807 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1121. Min Act: -0.0001

Data Index: 862868 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1081164 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1113. Min Act: -0.0001

Data Index: 272175 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1107. Min Act: -0.0002

Data Index: 1125252 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1093. Min Act: -0.0002

Data Index: 756109 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1078. Min Act: -0.0002

Data Index: 627998 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1091. Min Act: -0.0001

Data Index: 148632 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1222206 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1143. Min Act: -0.0001

Data Index: 752751 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1092. Min Act: -0.0002

Data Index: 787375 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1080. Min Act: -0.0001

Data Index: 252779 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1253622 (C4 (Web Text))

Max Activating Token Index: 519