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

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

Neuron 1085 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6781. Min Range: -2.6781

Max Act: 2.6781. Min Act: -0.0000

Data Index: 1605887 (Python Code)

Max Activating Token Index: 455

Text #1

Max Range: 2.6781. Min Range: -2.6781

Max Act: 2.5780. Min Act: -0.0001

Data Index: 1638101 (Python Code)

Max Activating Token Index: 703

Text #2

Max Range: 2.6781. Min Range: -2.6781

Max Act: 2.4372. Min Act: -0.0000

Data Index: 1508493 (Python Code)

Max Activating Token Index: 292

Text #3

Max Range: 2.6781. Min Range: -2.6781

Max Act: 2.2693. Min Act: -0.0000

Data Index: 1506220 (Python Code)

Max Activating Token Index: 497

Text #4

Max Range: 2.6781. Min Range: -2.6781

Max Act: 2.5217. Min Act: -0.0000

Data Index: 1547705 (Python Code)

Max Activating Token Index: 869

Text #5

Max Range: 2.6781. Min Range: -2.6781

Max Act: 2.3921. Min Act: -0.0001

Data Index: 1593695 (Python Code)

Max Activating Token Index: 740

Text #6

Max Range: 2.6781. Min Range: -2.6781

Max Act: 2.1996. Min Act: -0.0001

Data Index: 1371177 (Python Code)

Max Activating Token Index: 651

Text #7

Max Range: 2.6781. Min Range: -2.6781

Max Act: 2.2204. Min Act: -0.0000

Data Index: 1634912 (Python Code)

Max Activating Token Index: 408

Text #8

Max Range: 2.6781. Min Range: -2.6781

Max Act: 2.2236. Min Act: -0.0000

Data Index: 1655330 (Python Code)

Max Activating Token Index: 182

Text #9

Max Range: 2.6781. Min Range: -2.6781

Max Act: 2.2699. Min Act: -0.0000

Data Index: 1530133 (Python Code)

Max Activating Token Index: 433

Text #10

Max Range: 2.6781. Min Range: -2.6781

Max Act: 2.3281. Min Act: -0.0000

Data Index: 1580155 (Python Code)

Max Activating Token Index: 252

Text #11

Max Range: 2.6781. Min Range: -2.6781

Max Act: 2.2229. Min Act: -0.0000

Data Index: 1606160 (Python Code)

Max Activating Token Index: 268

Text #12

Max Range: 2.6781. Min Range: -2.6781

Max Act: 2.2795. Min Act: -0.0000

Data Index: 1565234 (Python Code)

Max Activating Token Index: 218

Text #13

Max Range: 2.6781. Min Range: -2.6781

Max Act: 2.2126. Min Act: -0.0000

Data Index: 1640375 (Python Code)

Max Activating Token Index: 682

Text #14

Max Range: 2.6781. Min Range: -2.6781

Max Act: 2.1480. Min Act: -0.0000

Data Index: 1400381 (Python Code)

Max Activating Token Index: 221

Text #15

Max Range: 2.6781. Min Range: -2.6781

Max Act: 2.0825. Min Act: -0.0001

Data Index: 1492561 (Python Code)

Max Activating Token Index: 774

Text #16

Max Range: 2.6781. Min Range: -2.6781

Max Act: 2.1882. Min Act: -0.0000

Data Index: 1609765 (Python Code)

Max Activating Token Index: 509

Text #17

Max Range: 2.6781. Min Range: -2.6781

Max Act: 1.9592. Min Act: -0.0000

Data Index: 1567735 (Python Code)

Max Activating Token Index: 331

Text #18

Max Range: 2.6781. Min Range: -2.6781

Max Act: 2.1005. Min Act: -0.0000

Data Index: 1616911 (Python Code)

Max Activating Token Index: 266

Text #19

Max Range: 2.6781. Min Range: -2.6781

Max Act: 2.0509. Min Act: -0.0000

Data Index: 1537383 (Python Code)

Max Activating Token Index: 552