Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2722 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 5.9397. Min Range: -5.9397

Max Act: 5.8780. Min Act: -0.0001

Data Index: 137483 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 5.9397. Min Range: -5.9397

Max Act: 5.3611. Min Act: -0.0001

Data Index: 726941 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 5.9397. Min Range: -5.9397

Max Act: 5.8597. Min Act: -0.0001

Data Index: 152334 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 5.9397. Min Range: -5.9397

Max Act: 5.9397. Min Act: -0.0001

Data Index: 616798 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 5.9397. Min Range: -5.9397

Max Act: 5.4302. Min Act: -0.0001

Data Index: 767960 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 5.9397. Min Range: -5.9397

Max Act: 4.8322. Min Act: -0.0001

Data Index: 956526 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 5.9397. Min Range: -5.9397

Max Act: 4.5064. Min Act: -0.0001

Data Index: 156800 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 5.9397. Min Range: -5.9397

Max Act: 5.2002. Min Act: -0.0001

Data Index: 852754 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 5.9397. Min Range: -5.9397

Max Act: 3.6067. Min Act: -0.0001

Data Index: 748452 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 5.9397. Min Range: -5.9397

Max Act: 3.9618. Min Act: -0.0001

Data Index: 606304 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 5.9397. Min Range: -5.9397

Max Act: 3.7452. Min Act: -0.0001

Data Index: 1220216 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 5.9397. Min Range: -5.9397

Max Act: 3.4735. Min Act: -0.0001

Data Index: 1312983 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 5.9397. Min Range: -5.9397

Max Act: 3.1191. Min Act: -0.0001

Data Index: 471124 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 5.9397. Min Range: -5.9397

Max Act: 3.6192. Min Act: -0.0001

Data Index: 631796 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 5.9397. Min Range: -5.9397

Max Act: 3.0032. Min Act: -0.0001

Data Index: 698788 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 5.9397. Min Range: -5.9397

Max Act: 3.2727. Min Act: -0.0001

Data Index: 29522 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 5.9397. Min Range: -5.9397

Max Act: 3.1756. Min Act: -0.0001

Data Index: 78428 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 5.9397. Min Range: -5.9397

Max Act: 3.4342. Min Act: -0.0001

Data Index: 639652 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 5.9397. Min Range: -5.9397

Max Act: 3.2772. Min Act: -0.0001

Data Index: 518081 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 5.9397. Min Range: -5.9397

Max Act: 3.0935. Min Act: -0.0001

Data Index: 1294202 (C4 (Web Text))

Max Activating Token Index: 66