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

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

Neuron 1417 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: 5.4872. Min Range: -5.4872

Max Act: 5.4872. Min Act: -0.0000

Data Index: 395852 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 5.4872. Min Range: -5.4872

Max Act: 5.2696. Min Act: -0.0000

Data Index: 864993 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 5.4872. Min Range: -5.4872

Max Act: 5.2481. Min Act: -0.0000

Data Index: 183522 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 5.4872. Min Range: -5.4872

Max Act: 5.2125. Min Act: -0.0000

Data Index: 570722 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 5.4872. Min Range: -5.4872

Max Act: 5.0031. Min Act: -0.0000

Data Index: 1309866 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 5.4872. Min Range: -5.4872

Max Act: 5.0210. Min Act: -0.0000

Data Index: 366428 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 5.4872. Min Range: -5.4872

Max Act: 4.9916. Min Act: -0.0000

Data Index: 407299 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 5.4872. Min Range: -5.4872

Max Act: 4.9447. Min Act: -0.0000

Data Index: 704170 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 5.4872. Min Range: -5.4872

Max Act: 4.7731. Min Act: -0.0000

Data Index: 1272129 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 5.4872. Min Range: -5.4872

Max Act: 5.1298. Min Act: -0.0000

Data Index: 1350477 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 5.4872. Min Range: -5.4872

Max Act: 5.0616. Min Act: -0.0000

Data Index: 920647 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 5.4872. Min Range: -5.4872

Max Act: 5.0641. Min Act: -0.0000

Data Index: 556336 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 5.4872. Min Range: -5.4872

Max Act: 5.0057. Min Act: -0.0000

Data Index: 517625 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 5.4872. Min Range: -5.4872

Max Act: 4.9789. Min Act: -0.0000

Data Index: 276651 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 5.4872. Min Range: -5.4872

Max Act: 4.8374. Min Act: -0.0000

Data Index: 258402 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 5.4872. Min Range: -5.4872

Max Act: 5.0150. Min Act: -0.0000

Data Index: 485065 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 5.4872. Min Range: -5.4872

Max Act: 5.0090. Min Act: -0.0000

Data Index: 169567 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 5.4872. Min Range: -5.4872

Max Act: 4.9133. Min Act: -0.0000

Data Index: 730181 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 5.4872. Min Range: -5.4872

Max Act: 4.9723. Min Act: -0.0000

Data Index: 22030 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 5.4872. Min Range: -5.4872

Max Act: 5.0050. Min Act: -0.0000

Data Index: 943541 (C4 (Web Text))

Max Activating Token Index: 166