Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 824 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3606. Min Range: -2.3606

Max Act: 2.3606. Min Act: -0.0000

Data Index: 821261 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 2.3606. Min Range: -2.3606

Max Act: 2.1592. Min Act: -0.0000

Data Index: 489313 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 2.3606. Min Range: -2.3606

Max Act: 2.0956. Min Act: -0.0000

Data Index: 593873 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 2.3606. Min Range: -2.3606

Max Act: 1.7310. Min Act: -0.0000

Data Index: 74621 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 2.3606. Min Range: -2.3606

Max Act: 1.8066. Min Act: -0.0000

Data Index: 819235 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 2.3606. Min Range: -2.3606

Max Act: 1.8386. Min Act: -0.0000

Data Index: 1143989 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 2.3606. Min Range: -2.3606

Max Act: 1.7447. Min Act: -0.0000

Data Index: 1139842 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 2.3606. Min Range: -2.3606

Max Act: 1.7192. Min Act: -0.0000

Data Index: 569960 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 2.3606. Min Range: -2.3606

Max Act: 1.6400. Min Act: -0.0000

Data Index: 833188 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 2.3606. Min Range: -2.3606

Max Act: 1.7738. Min Act: -0.0000

Data Index: 1194256 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 2.3606. Min Range: -2.3606

Max Act: 1.5634. Min Act: -0.0000

Data Index: 962787 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 2.3606. Min Range: -2.3606

Max Act: 1.6509. Min Act: -0.0000

Data Index: 494509 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 2.3606. Min Range: -2.3606

Max Act: 1.5722. Min Act: -0.0000

Data Index: 919643 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 2.3606. Min Range: -2.3606

Max Act: 1.5467. Min Act: -0.0000

Data Index: 1317097 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 2.3606. Min Range: -2.3606

Max Act: 1.5359. Min Act: -0.0000

Data Index: 219333 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 2.3606. Min Range: -2.3606

Max Act: 1.6134. Min Act: -0.0000

Data Index: 447175 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 2.3606. Min Range: -2.3606

Max Act: 1.5022. Min Act: -0.0000

Data Index: 381692 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 2.3606. Min Range: -2.3606

Max Act: 1.3843. Min Act: -0.0000

Data Index: 1146059 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 2.3606. Min Range: -2.3606

Max Act: 1.4728. Min Act: -0.0000

Data Index: 579479 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 2.3606. Min Range: -2.3606

Max Act: 1.3676. Min Act: -0.0000

Data Index: 1120211 (C4 (Web Text))

Max Activating Token Index: 723