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

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

Neuron 3614 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0502. Min Range: -1.0502

Max Act: 1.0502. Min Act: -0.0001

Data Index: 1346133 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 1.0502. Min Range: -1.0502

Max Act: 1.0130. Min Act: -0.0002

Data Index: 476075 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9916. Min Act: -0.0001

Data Index: 878897 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8778. Min Act: -0.0002

Data Index: 1358418 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9845. Min Act: -0.0001

Data Index: 723494 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9604. Min Act: -0.0001

Data Index: 14799 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9251. Min Act: -0.0001

Data Index: 692727 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8916. Min Act: -0.0001

Data Index: 375105 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8993. Min Act: -0.0001

Data Index: 430876 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8630. Min Act: -0.0001

Data Index: 1132071 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9205. Min Act: -0.0001

Data Index: 333022 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8691. Min Act: -0.0001

Data Index: 265458 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8861. Min Act: -0.0001

Data Index: 51837 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9444. Min Act: -0.0001

Data Index: 1112132 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8850. Min Act: -0.0001

Data Index: 54677 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9069. Min Act: -0.0001

Data Index: 381991 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8546. Min Act: -0.0001

Data Index: 1084743 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9044. Min Act: -0.0001

Data Index: 833474 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9315. Min Act: -0.0001

Data Index: 129664 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8787. Min Act: -0.0001

Data Index: 20574 (C4 (Web Text))

Max Activating Token Index: 556