Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1301 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6793. Min Act: -0.0004

Data Index: 530624 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.4938. Min Act: -0.0004

Data Index: 1459543 (Python Code)

Max Activating Token Index: 871

Text #2

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6729. Min Act: -0.0004

Data Index: 766990 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.8415. Min Act: -0.0004

Data Index: 755661 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6090. Min Act: -0.0004

Data Index: 313680 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6645. Min Act: -0.0004

Data Index: 980486 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6430. Min Act: -0.0004

Data Index: 1188681 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6174. Min Act: -0.0004

Data Index: 354305 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.5734. Min Act: -0.0004

Data Index: 1044889 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.5622. Min Act: -0.0004

Data Index: 802668 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6632. Min Act: -0.0004

Data Index: 139763 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7058. Min Act: -0.0004

Data Index: 822778 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6208. Min Act: -0.0004

Data Index: 701903 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6207. Min Act: -0.0004

Data Index: 776136 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.5798. Min Act: -0.0004

Data Index: 446831 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6557. Min Act: -0.0004

Data Index: 531353 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.5882. Min Act: -0.0004

Data Index: 886044 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.5717. Min Act: -0.0004

Data Index: 1307128 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.5633. Min Act: -0.0004

Data Index: 1590879 (Python Code)

Max Activating Token Index: 295

Text #19

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.5178. Min Act: -0.0004

Data Index: 624099 (C4 (Web Text))

Max Activating Token Index: 316