Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3542 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1091071 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1074823 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1280. Min Act: -0.0000

Data Index: 87175 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1134224 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1124263 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1324. Min Act: -0.0000

Data Index: 841113 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1165. Min Act: -0.0000

Data Index: 669106 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1116. Min Act: -0.0000

Data Index: 391263 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1044. Min Act: -0.0000

Data Index: 1246996 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1050. Min Act: -0.0000

Data Index: 970034 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1079740 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1263. Min Act: -0.0000

Data Index: 913327 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1179. Min Act: -0.0000

Data Index: 995830 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1114. Min Act: -0.0000

Data Index: 1407484 (Python Code)

Max Activating Token Index: 498

Text #14

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1089796 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1043. Min Act: -0.0000

Data Index: 46919 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1062. Min Act: -0.0000

Data Index: 1212599 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1111. Min Act: -0.0000

Data Index: 12199 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1069. Min Act: -0.0000

Data Index: 483324 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1072. Min Act: -0.0000

Data Index: 419974 (C4 (Web Text))

Max Activating Token Index: 973