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

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

Neuron 4885 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: 2.3283. Min Range: -2.3283

Max Act: 2.3283. Min Act: -0.0000

Data Index: 718484 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 2.3283. Min Range: -2.3283

Max Act: 2.0621. Min Act: -0.0000

Data Index: 304069 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 2.3283. Min Range: -2.3283

Max Act: 2.1192. Min Act: -0.0000

Data Index: 777883 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 2.3283. Min Range: -2.3283

Max Act: 2.1908. Min Act: -0.0000

Data Index: 299798 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 2.3283. Min Range: -2.3283

Max Act: 1.9608. Min Act: -0.0000

Data Index: 1230728 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 2.3283. Min Range: -2.3283

Max Act: 1.9199. Min Act: -0.0000

Data Index: 820383 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 2.3283. Min Range: -2.3283

Max Act: 2.0173. Min Act: -0.0000

Data Index: 1127361 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 2.3283. Min Range: -2.3283

Max Act: 1.9138. Min Act: -0.0000

Data Index: 1179568 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 2.3283. Min Range: -2.3283

Max Act: 1.7571. Min Act: -0.0000

Data Index: 448761 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 2.3283. Min Range: -2.3283

Max Act: 1.6944. Min Act: -0.0000

Data Index: 1092436 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 2.3283. Min Range: -2.3283

Max Act: 1.7809. Min Act: -0.0000

Data Index: 173291 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 2.3283. Min Range: -2.3283

Max Act: 1.8491. Min Act: -0.0000

Data Index: 22721 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 2.3283. Min Range: -2.3283

Max Act: 1.8415. Min Act: -0.0000

Data Index: 354708 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 2.3283. Min Range: -2.3283

Max Act: 1.7296. Min Act: -0.0000

Data Index: 1101687 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 2.3283. Min Range: -2.3283

Max Act: 1.7136. Min Act: -0.0000

Data Index: 1113223 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 2.3283. Min Range: -2.3283

Max Act: 1.7132. Min Act: -0.0000

Data Index: 822754 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 2.3283. Min Range: -2.3283

Max Act: 1.7086. Min Act: -0.0000

Data Index: 1003361 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 2.3283. Min Range: -2.3283

Max Act: 1.6827. Min Act: -0.0000

Data Index: 424031 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 2.3283. Min Range: -2.3283

Max Act: 1.6631. Min Act: -0.0000

Data Index: 527206 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 2.3283. Min Range: -2.3283

Max Act: 1.6531. Min Act: -0.0000

Data Index: 645819 (C4 (Web Text))

Max Activating Token Index: 236