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

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

Neuron 5032 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: 7.7461. Min Range: -7.7461

Max Act: 7.7461. Min Act: -0.0000

Data Index: 227213 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 7.7461. Min Range: -7.7461

Max Act: 5.7516. Min Act: 0.0000

Data Index: 297537 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 7.7461. Min Range: -7.7461

Max Act: 5.7615. Min Act: -0.0000

Data Index: 1088926 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 7.7461. Min Range: -7.7461

Max Act: 5.3043. Min Act: -0.0000

Data Index: 278538 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 7.7461. Min Range: -7.7461

Max Act: 5.7424. Min Act: -0.0000

Data Index: 209253 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 7.7461. Min Range: -7.7461

Max Act: 4.9476. Min Act: -0.0000

Data Index: 296478 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 7.7461. Min Range: -7.7461

Max Act: 5.1753. Min Act: -0.0000

Data Index: 861843 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 7.7461. Min Range: -7.7461

Max Act: 4.7704. Min Act: 0.0000

Data Index: 375035 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 7.7461. Min Range: -7.7461

Max Act: 5.0057. Min Act: 0.0000

Data Index: 1205894 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 7.7461. Min Range: -7.7461

Max Act: 3.9775. Min Act: -0.0000

Data Index: 502589 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 7.7461. Min Range: -7.7461

Max Act: 4.2870. Min Act: -0.0000

Data Index: 392816 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 7.7461. Min Range: -7.7461

Max Act: 3.7579. Min Act: -0.0000

Data Index: 1160227 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 7.7461. Min Range: -7.7461

Max Act: 3.1271. Min Act: -0.0000

Data Index: 264907 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 7.7461. Min Range: -7.7461

Max Act: 4.3458. Min Act: 0.0000

Data Index: 544463 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 7.7461. Min Range: -7.7461

Max Act: 4.1224. Min Act: -0.0000

Data Index: 1249192 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 7.7461. Min Range: -7.7461

Max Act: 4.2046. Min Act: -0.0000

Data Index: 820125 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 7.7461. Min Range: -7.7461

Max Act: 3.5985. Min Act: -0.0000

Data Index: 78528 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 7.7461. Min Range: -7.7461

Max Act: 4.0609. Min Act: 0.0000

Data Index: 421609 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 7.7461. Min Range: -7.7461

Max Act: 4.0563. Min Act: -0.0000

Data Index: 799238 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 7.7461. Min Range: -7.7461

Max Act: 3.3023. Min Act: -0.0000

Data Index: 957128 (C4 (Web Text))

Max Activating Token Index: 298