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

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

Neuron 6066 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2130. Min Range: -1.2130

Max Act: 1.2130. Min Act: -0.0000

Data Index: 887096 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 1.2130. Min Range: -1.2130

Max Act: 1.0610. Min Act: -0.0000

Data Index: 362959 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.9988. Min Act: -0.0000

Data Index: 1515998 (Python Code)

Max Activating Token Index: 202

Text #3

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.9382. Min Act: -0.0000

Data Index: 165928 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.9335. Min Act: -0.0000

Data Index: 1519308 (Python Code)

Max Activating Token Index: 956

Text #5

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.9184. Min Act: -0.0000

Data Index: 1369313 (Python Code)

Max Activating Token Index: 724

Text #6

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1438411 (Python Code)

Max Activating Token Index: 369

Text #7

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.8673. Min Act: -0.0000

Data Index: 473864 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1206946 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.8286. Min Act: -0.0000

Data Index: 1500485 (Python Code)

Max Activating Token Index: 56

Text #10

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.8063. Min Act: -0.0000

Data Index: 336966 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.8209. Min Act: -0.0000

Data Index: 148361 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.8153. Min Act: -0.0000

Data Index: 958459 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.8426. Min Act: -0.0000

Data Index: 568385 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1134177 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1477353 (Python Code)

Max Activating Token Index: 230

Text #16

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.8592. Min Act: -0.0000

Data Index: 414112 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.7929. Min Act: -0.0000

Data Index: 82547 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.7220. Min Act: -0.0000

Data Index: 941526 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.7816. Min Act: -0.0000

Data Index: 1644135 (Python Code)

Max Activating Token Index: 55