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

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

Neuron 3536 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1218. Min Act: -0.0001

Data Index: 298795 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1145. Min Act: -0.0001

Data Index: 176099 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1116. Min Act: -0.0001

Data Index: 138663 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1126. Min Act: -0.0001

Data Index: 856837 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1053. Min Act: -0.0001

Data Index: 388432 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1046. Min Act: -0.0001

Data Index: 181522 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1027. Min Act: -0.0001

Data Index: 67827 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1094. Min Act: -0.0001

Data Index: 1149241 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1051. Min Act: -0.0001

Data Index: 451661 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1037. Min Act: -0.0001

Data Index: 54248 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1001. Min Act: -0.0001

Data Index: 867189 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1060. Min Act: -0.0001

Data Index: 495138 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0992. Min Act: -0.0001

Data Index: 1170997 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1051. Min Act: -0.0001

Data Index: 79729 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1203828 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1020. Min Act: -0.0001

Data Index: 1011229 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1004. Min Act: -0.0001

Data Index: 506894 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0925. Min Act: -0.0001

Data Index: 740123 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1113614 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1236016 (C4 (Web Text))

Max Activating Token Index: 913