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

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

Neuron 3266 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: 1.3685. Min Range: -1.3685

Max Act: 1.3685. Min Act: -0.0002

Data Index: 940347 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 1.3685. Min Range: -1.3685

Max Act: 1.2178. Min Act: -0.0002

Data Index: 1116856 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 1.3685. Min Range: -1.3685

Max Act: 1.1349. Min Act: -0.0002

Data Index: 527162 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.9271. Min Act: -0.0002

Data Index: 745176 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 1.3685. Min Range: -1.3685

Max Act: 1.0626. Min Act: -0.0001

Data Index: 1289362 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 1.3685. Min Range: -1.3685

Max Act: 1.0816. Min Act: -0.0001

Data Index: 728783 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.9744. Min Act: -0.0002

Data Index: 1277772 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.9987. Min Act: -0.0002

Data Index: 1341658 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 1.3685. Min Range: -1.3685

Max Act: 1.0177. Min Act: -0.0002

Data Index: 1322269 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.9434. Min Act: -0.0002

Data Index: 895453 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.9375. Min Act: -0.0002

Data Index: 1304556 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.9367. Min Act: -0.0002

Data Index: 433837 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.9881. Min Act: -0.0001

Data Index: 60395 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.8550. Min Act: -0.0002

Data Index: 326048 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.8998. Min Act: -0.0002

Data Index: 225907 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.9108. Min Act: -0.0001

Data Index: 749245 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.9017. Min Act: -0.0002

Data Index: 427767 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.9247. Min Act: -0.0002

Data Index: 750114 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.9247. Min Act: -0.0001

Data Index: 1301255 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 1.3685. Min Range: -1.3685

Max Act: 0.9678. Min Act: -0.0002

Data Index: 392148 (C4 (Web Text))

Max Activating Token Index: 731