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

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

Neuron 3030 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1332. Min Act: -0.0001

Data Index: 1245780 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1269. Min Act: -0.0001

Data Index: 1332285 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1188. Min Act: -0.0001

Data Index: 221113 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1115491 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1153. Min Act: -0.0001

Data Index: 398188 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1145. Min Act: -0.0001

Data Index: 291116 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1223. Min Act: -0.0001

Data Index: 680233 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1136. Min Act: -0.0001

Data Index: 962156 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1342203 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1096310 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1138. Min Act: -0.0001

Data Index: 388823 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1095. Min Act: -0.0001

Data Index: 948565 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1136. Min Act: -0.0001

Data Index: 71015 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1118. Min Act: -0.0001

Data Index: 814042 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1038. Min Act: -0.0001

Data Index: 969285 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1074. Min Act: -0.0001

Data Index: 275307 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1109. Min Act: -0.0001

Data Index: 90778 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0997. Min Act: -0.0001

Data Index: 258411 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1057. Min Act: -0.0001

Data Index: 943406 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1139. Min Act: -0.0001

Data Index: 1190501 (C4 (Web Text))

Max Activating Token Index: 714