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

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

Neuron 2790 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: 0.1468. Min Range: -0.1468

Max Act: 0.1468. Min Act: -0.0001

Data Index: 847640 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1274. Min Act: -0.0002

Data Index: 434669 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1241. Min Act: -0.0001

Data Index: 564864 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1157. Min Act: -0.0001

Data Index: 570880 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1187. Min Act: -0.0001

Data Index: 624954 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1156. Min Act: -0.0001

Data Index: 286286 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1061520 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1092. Min Act: -0.0001

Data Index: 1349821 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1039. Min Act: -0.0001

Data Index: 683120 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0996. Min Act: -0.0002

Data Index: 1266276 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1059. Min Act: -0.0001

Data Index: 592798 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0962. Min Act: -0.0001

Data Index: 514341 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0993. Min Act: -0.0001

Data Index: 317242 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0979. Min Act: -0.0001

Data Index: 729483 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0974. Min Act: -0.0002

Data Index: 379941 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0969. Min Act: -0.0002

Data Index: 401128 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0964. Min Act: -0.0001

Data Index: 1245767 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0953. Min Act: -0.0002

Data Index: 364637 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0950. Min Act: -0.0002

Data Index: 1039101 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0949. Min Act: -0.0002

Data Index: 786760 (C4 (Web Text))

Max Activating Token Index: 19