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

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

Neuron 1998 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1318. Min Act: -0.0003

Data Index: 624729 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1268. Min Act: -0.0002

Data Index: 80480 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1235. Min Act: -0.0003

Data Index: 91108 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1208. Min Act: -0.0003

Data Index: 873177 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1205. Min Act: -0.0003

Data Index: 1250512 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1197. Min Act: -0.0003

Data Index: 137793 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1166. Min Act: -0.0003

Data Index: 1332743 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1132. Min Act: -0.0003

Data Index: 1154886 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1125. Min Act: -0.0003

Data Index: 61162 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1114. Min Act: -0.0003

Data Index: 1325427 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1104. Min Act: -0.0003

Data Index: 583424 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1108. Min Act: -0.0003

Data Index: 915872 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1065. Min Act: -0.0003

Data Index: 921800 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1082. Min Act: -0.0003

Data Index: 45067 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1061. Min Act: -0.0003

Data Index: 1329201 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1016. Min Act: -0.0003

Data Index: 530001 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1049. Min Act: -0.0003

Data Index: 344642 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1029. Min Act: -0.0003

Data Index: 99073 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1020. Min Act: -0.0003

Data Index: 406325 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.0997. Min Act: -0.0003

Data Index: 402389 (C4 (Web Text))

Max Activating Token Index: 45