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

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

Neuron 2638 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.8558. Min Act: -0.0001

Data Index: 689086 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.6393. Min Act: -0.0001

Data Index: 756838 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.7428. Min Act: -0.0001

Data Index: 121825 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.5063. Min Act: -0.0001

Data Index: 1014757 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.5678. Min Act: -0.0001

Data Index: 1082253 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.6008. Min Act: -0.0001

Data Index: 89110 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.5597. Min Act: -0.0001

Data Index: 127329 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.3873. Min Act: -0.0001

Data Index: 208205 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.3794. Min Act: -0.0001

Data Index: 679822 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.5386. Min Act: -0.0001

Data Index: 520366 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.4361. Min Act: -0.0001

Data Index: 454486 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.6940. Min Act: -0.0001

Data Index: 837658 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.5228. Min Act: -0.0001

Data Index: 1197682 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.4221. Min Act: -0.0001

Data Index: 684254 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.4185. Min Act: -0.0001

Data Index: 1034796 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.5788. Min Act: -0.0001

Data Index: 1346854 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.4162. Min Act: -0.0001

Data Index: 226585 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.4502. Min Act: -0.0001

Data Index: 1227922 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.4128. Min Act: -0.0001

Data Index: 1021237 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.3631. Min Act: -0.0001

Data Index: 1117385 (C4 (Web Text))

Max Activating Token Index: 591