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

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

Neuron 2303 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.8519. Min Act: -0.0001

Data Index: 1051422 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.8642. Min Act: -0.0001

Data Index: 364266 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.8076. Min Act: -0.0001

Data Index: 896863 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7319. Min Act: -0.0001

Data Index: 984895 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7277. Min Act: -0.0001

Data Index: 833642 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7059. Min Act: -0.0001

Data Index: 242210 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6769. Min Act: -0.0001

Data Index: 237325 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6951. Min Act: -0.0001

Data Index: 1110955 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7335. Min Act: -0.0001

Data Index: 776738 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6677. Min Act: -0.0001

Data Index: 1154616 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6278. Min Act: -0.0001

Data Index: 67380 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7025. Min Act: -0.0001

Data Index: 1062829 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6322. Min Act: -0.0001

Data Index: 1169973 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6973. Min Act: -0.0001

Data Index: 1283506 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6490. Min Act: -0.0001

Data Index: 1039498 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6475. Min Act: -0.0001

Data Index: 758597 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6481. Min Act: -0.0001

Data Index: 1145237 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6426. Min Act: -0.0001

Data Index: 889700 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6458. Min Act: -0.0001

Data Index: 758293 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6631. Min Act: -0.0001

Data Index: 161886 (C4 (Web Text))

Max Activating Token Index: 199