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

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

Neuron 2411 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1884. Min Act: -0.0003

Data Index: 715290 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1344. Min Act: -0.0003

Data Index: 621716 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1550. Min Act: -0.0003

Data Index: 930982 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1781. Min Act: -0.0002

Data Index: 1031850 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1277. Min Act: -0.0003

Data Index: 924195 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1270. Min Act: -0.0003

Data Index: 988558 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1352. Min Act: -0.0003

Data Index: 1329779 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1383. Min Act: -0.0003

Data Index: 1319393 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1136. Min Act: -0.0003

Data Index: 966514 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1185. Min Act: -0.0003

Data Index: 506287 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1050. Min Act: -0.0003

Data Index: 806262 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.0967. Min Act: -0.0003

Data Index: 981167 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1111. Min Act: -0.0003

Data Index: 1053107 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1095. Min Act: -0.0003

Data Index: 1293405 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.0735. Min Act: -0.0003

Data Index: 503509 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.0746. Min Act: -0.0003

Data Index: 829796 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.0646. Min Act: -0.0003

Data Index: 1278789 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1257. Min Act: -0.0002

Data Index: 887512 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1316. Min Act: -0.0002

Data Index: 1068854 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1174. Min Act: -0.0003

Data Index: 1298670 (C4 (Web Text))

Max Activating Token Index: 1023