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

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

Neuron 3516 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: 0.1336. Min Range: -0.1336

Max Act: 0.1336. Min Act: -0.0001

Data Index: 1262428 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1296. Min Act: -0.0002

Data Index: 1014204 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1189. Min Act: -0.0002

Data Index: 653097 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1066302 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1069187 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1037. Min Act: -0.0002

Data Index: 153176 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1126. Min Act: -0.0001

Data Index: 335084 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1035. Min Act: -0.0002

Data Index: 510884 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1081. Min Act: -0.0002

Data Index: 260498 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0911. Min Act: -0.0002

Data Index: 683249 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0912. Min Act: -0.0001

Data Index: 296401 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1014. Min Act: -0.0002

Data Index: 894897 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0935. Min Act: -0.0002

Data Index: 921906 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0972. Min Act: -0.0001

Data Index: 246128 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1063. Min Act: -0.0001

Data Index: 842366 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1022. Min Act: -0.0001

Data Index: 304954 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0944. Min Act: -0.0001

Data Index: 687199 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0941. Min Act: -0.0001

Data Index: 121856 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0931. Min Act: -0.0001

Data Index: 1205781 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0974. Min Act: -0.0001

Data Index: 395754 (C4 (Web Text))

Max Activating Token Index: 338