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

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

Neuron 778 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: 0.9170. Min Range: -0.9170

Max Act: 0.9170. Min Act: -0.0000

Data Index: 263298 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.8431. Min Act: -0.0000

Data Index: 407627 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.7903. Min Act: -0.0001

Data Index: 193655 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1022378 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.7380. Min Act: -0.0000

Data Index: 971568 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.7686. Min Act: -0.0000

Data Index: 987847 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.7309. Min Act: -0.0000

Data Index: 687847 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.7063. Min Act: -0.0000

Data Index: 284245 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.6756. Min Act: -0.0001

Data Index: 1009558 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.6814. Min Act: -0.0000

Data Index: 1147626 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.6822. Min Act: -0.0000

Data Index: 766941 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.7060. Min Act: -0.0001

Data Index: 1336523 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.6918. Min Act: -0.0000

Data Index: 154237 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.6675. Min Act: -0.0000

Data Index: 986340 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.6768. Min Act: -0.0000

Data Index: 457785 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.6684. Min Act: -0.0001

Data Index: 101383 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.6489. Min Act: -0.0001

Data Index: 867470 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.6577. Min Act: -0.0000

Data Index: 303373 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.5960. Min Act: -0.0001

Data Index: 1158674 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.6599. Min Act: -0.0001

Data Index: 372300 (C4 (Web Text))

Max Activating Token Index: 62