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

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

Neuron 5098 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2736. Min Act: -0.0000

Data Index: 149945 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1338737 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1010881 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1266462 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2178. Min Act: -0.0000

Data Index: 952575 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.2131. Min Act: -0.0000

Data Index: 833362 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1894. Min Act: -0.0000

Data Index: 131820 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1848. Min Act: -0.0000

Data Index: 4639 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1759. Min Act: -0.0000

Data Index: 843991 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1668. Min Act: -0.0000

Data Index: 613015 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1641. Min Act: -0.0000

Data Index: 771857 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1740. Min Act: -0.0000

Data Index: 986573 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1640. Min Act: -0.0000

Data Index: 1349302 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1603. Min Act: -0.0000

Data Index: 353156 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1649. Min Act: -0.0000

Data Index: 1222111 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1534. Min Act: -0.0000

Data Index: 1145572 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1514. Min Act: -0.0000

Data Index: 80655 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1607. Min Act: -0.0000

Data Index: 505295 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1549. Min Act: -0.0000

Data Index: 118467 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.2736. Min Range: -0.2736

Max Act: 0.1562. Min Act: -0.0000

Data Index: 894324 (C4 (Web Text))

Max Activating Token Index: 574