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

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

Neuron 4822 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.8864. Min Act: -0.0000

Data Index: 491523 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.9179. Min Act: -0.0000

Data Index: 400384 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.8788. Min Act: -0.0000

Data Index: 836888 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.8180. Min Act: -0.0000

Data Index: 29169 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.8976. Min Act: -0.0000

Data Index: 972705 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.8259. Min Act: -0.0000

Data Index: 979683 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7734. Min Act: -0.0000

Data Index: 474639 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7829. Min Act: -0.0000

Data Index: 844431 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.8309. Min Act: -0.0000

Data Index: 176412 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1017100 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.8101. Min Act: -0.0000

Data Index: 868694 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7897. Min Act: -0.0000

Data Index: 1264376 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7996. Min Act: -0.0000

Data Index: 817250 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7466. Min Act: -0.0000

Data Index: 397929 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7424. Min Act: -0.0000

Data Index: 472336 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7125. Min Act: -0.0000

Data Index: 143190 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7345. Min Act: -0.0000

Data Index: 1348950 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7624. Min Act: -0.0000

Data Index: 537050 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7142. Min Act: -0.0000

Data Index: 18062 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7453. Min Act: -0.0000

Data Index: 328663 (C4 (Web Text))

Max Activating Token Index: 143