Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4506 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7302. Min Range: -4.7302

Max Act: 4.7302. Min Act: -0.0000

Data Index: 606658 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 4.7302. Min Range: -4.7302

Max Act: 4.0086. Min Act: -0.0000

Data Index: 967801 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 4.7302. Min Range: -4.7302

Max Act: 4.1407. Min Act: -0.0000

Data Index: 956130 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 4.7302. Min Range: -4.7302

Max Act: 3.7385. Min Act: -0.0000

Data Index: 596337 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 4.7302. Min Range: -4.7302

Max Act: 3.5452. Min Act: -0.0000

Data Index: 518151 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 4.7302. Min Range: -4.7302

Max Act: 3.5031. Min Act: -0.0000

Data Index: 991671 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 4.7302. Min Range: -4.7302

Max Act: 3.4244. Min Act: -0.0000

Data Index: 100088 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 4.7302. Min Range: -4.7302

Max Act: 3.3935. Min Act: -0.0000

Data Index: 1118296 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 4.7302. Min Range: -4.7302

Max Act: 3.2100. Min Act: -0.0000

Data Index: 217782 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 4.7302. Min Range: -4.7302

Max Act: 3.2018. Min Act: -0.0000

Data Index: 1103894 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 4.7302. Min Range: -4.7302

Max Act: 3.2220. Min Act: -0.0000

Data Index: 91660 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 4.7302. Min Range: -4.7302

Max Act: 3.3014. Min Act: -0.0000

Data Index: 1065707 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 4.7302. Min Range: -4.7302

Max Act: 3.1009. Min Act: -0.0000

Data Index: 534763 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 4.7302. Min Range: -4.7302

Max Act: 3.2193. Min Act: -0.0000

Data Index: 1230498 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 4.7302. Min Range: -4.7302

Max Act: 3.3414. Min Act: -0.0000

Data Index: 706221 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 4.7302. Min Range: -4.7302

Max Act: 3.1654. Min Act: -0.0000

Data Index: 150069 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 4.7302. Min Range: -4.7302

Max Act: 2.9993. Min Act: -0.0000

Data Index: 314528 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 4.7302. Min Range: -4.7302

Max Act: 3.2648. Min Act: -0.0000

Data Index: 1331164 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 4.7302. Min Range: -4.7302

Max Act: 3.1739. Min Act: -0.0000

Data Index: 453786 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 4.7302. Min Range: -4.7302

Max Act: 2.9571. Min Act: -0.0000

Data Index: 791363 (C4 (Web Text))

Max Activating Token Index: 383