Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3710 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.4396. Min Act: -0.0000

Data Index: 370734 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3728. Min Act: -0.0000

Data Index: 167767 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3714. Min Act: -0.0000

Data Index: 545115 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1198256 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3442. Min Act: -0.0001

Data Index: 728284 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3396. Min Act: -0.0000

Data Index: 223795 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3148. Min Act: -0.0000

Data Index: 1218854 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3057. Min Act: -0.0000

Data Index: 36804 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.2973. Min Act: -0.0000

Data Index: 438368 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.2723. Min Act: -0.0000

Data Index: 214585 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3011. Min Act: -0.0000

Data Index: 389543 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.2915. Min Act: -0.0000

Data Index: 160736 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.2898. Min Act: -0.0000

Data Index: 985521 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.2917. Min Act: -0.0000

Data Index: 536810 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.2671. Min Act: -0.0001

Data Index: 36803 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.2723. Min Act: -0.0000

Data Index: 331405 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.2640. Min Act: -0.0000

Data Index: 767748 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.2697. Min Act: -0.0000

Data Index: 1150738 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1331940 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1030874 (C4 (Web Text))

Max Activating Token Index: 305