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

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

Neuron 1714 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: 1.5582. Min Range: -1.5582

Max Act: 1.5575. Min Act: -0.0001

Data Index: 863550 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 1.5582. Min Range: -1.5582

Max Act: 1.5582. Min Act: -0.0001

Data Index: 762953 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 1.5582. Min Range: -1.5582

Max Act: 1.4116. Min Act: -0.0001

Data Index: 739992 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 1.5582. Min Range: -1.5582

Max Act: 1.3900. Min Act: -0.0001

Data Index: 50986 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 1.5582. Min Range: -1.5582

Max Act: 1.4316. Min Act: -0.0001

Data Index: 631232 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 1.5582. Min Range: -1.5582

Max Act: 1.4032. Min Act: -0.0001

Data Index: 67277 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 1.5582. Min Range: -1.5582

Max Act: 1.4086. Min Act: -0.0001

Data Index: 807587 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 1.5582. Min Range: -1.5582

Max Act: 1.3650. Min Act: -0.0001

Data Index: 344802 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 1.5582. Min Range: -1.5582

Max Act: 1.2254. Min Act: -0.0001

Data Index: 940642 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 1.5582. Min Range: -1.5582

Max Act: 1.4171. Min Act: -0.0001

Data Index: 306219 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 1.5582. Min Range: -1.5582

Max Act: 1.3774. Min Act: -0.0001

Data Index: 662129 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 1.5582. Min Range: -1.5582

Max Act: 1.3630. Min Act: -0.0001

Data Index: 1336278 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 1.5582. Min Range: -1.5582

Max Act: 1.2671. Min Act: -0.0001

Data Index: 619737 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 1.5582. Min Range: -1.5582

Max Act: 1.4488. Min Act: -0.0001

Data Index: 251834 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 1.5582. Min Range: -1.5582

Max Act: 1.2186. Min Act: -0.0001

Data Index: 1133061 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 1.5582. Min Range: -1.5582

Max Act: 1.2112. Min Act: -0.0001

Data Index: 682561 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 1.5582. Min Range: -1.5582

Max Act: 1.2070. Min Act: -0.0001

Data Index: 657149 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 1.5582. Min Range: -1.5582

Max Act: 1.1978. Min Act: -0.0001

Data Index: 485698 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 1.5582. Min Range: -1.5582

Max Act: 1.2339. Min Act: -0.0001

Data Index: 174376 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 1.5582. Min Range: -1.5582

Max Act: 1.1989. Min Act: -0.0001

Data Index: 1135806 (C4 (Web Text))

Max Activating Token Index: 352