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

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

Neuron 1500 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: 0.1349. Min Range: -0.1349

Max Act: 0.1349. Min Act: -0.0001

Data Index: 230147 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1260. Min Act: -0.0002

Data Index: 68079 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1275. Min Act: -0.0002

Data Index: 303943 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1225. Min Act: -0.0001

Data Index: 339988 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1211. Min Act: -0.0001

Data Index: 816243 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1202. Min Act: -0.0001

Data Index: 665462 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1142. Min Act: -0.0001

Data Index: 846511 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1233. Min Act: -0.0001

Data Index: 658681 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1172. Min Act: -0.0001

Data Index: 521469 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1087. Min Act: -0.0001

Data Index: 342829 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1132. Min Act: -0.0002

Data Index: 511124 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1128. Min Act: -0.0001

Data Index: 402167 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1121. Min Act: -0.0001

Data Index: 107232 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1160. Min Act: -0.0001

Data Index: 365320 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1044. Min Act: -0.0001

Data Index: 609192 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1107. Min Act: -0.0001

Data Index: 1201593 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1118. Min Act: -0.0001

Data Index: 1259849 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1147. Min Act: -0.0001

Data Index: 1108063 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1061. Min Act: -0.0001

Data Index: 349637 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.1349. Min Range: -0.1349

Max Act: 0.1095. Min Act: -0.0002

Data Index: 1288816 (C4 (Web Text))

Max Activating Token Index: 975