Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3752 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.7778. Min Act: -0.0002

Data Index: 1347547 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.7671. Min Act: -0.0002

Data Index: 683992 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.7419. Min Act: -0.0002

Data Index: 1100662 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.7507. Min Act: -0.0002

Data Index: 534657 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.7317. Min Act: -0.0002

Data Index: 138183 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.7238. Min Act: -0.0002

Data Index: 756304 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.7153. Min Act: -0.0002

Data Index: 1152438 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.7109. Min Act: -0.0002

Data Index: 110367 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.7076. Min Act: -0.0002

Data Index: 1358231 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.7108. Min Act: -0.0002

Data Index: 261293 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6889. Min Act: -0.0002

Data Index: 1254879 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6770. Min Act: -0.0002

Data Index: 92209 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6997. Min Act: -0.0002

Data Index: 343835 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6703. Min Act: -0.0002

Data Index: 218832 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6726. Min Act: -0.0002

Data Index: 306956 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6778. Min Act: -0.0002

Data Index: 215937 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6807. Min Act: -0.0002

Data Index: 74545 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6699. Min Act: -0.0002

Data Index: 1328340 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6654. Min Act: -0.0003

Data Index: 250954 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6398. Min Act: -0.0002

Data Index: 90577 (C4 (Web Text))

Max Activating Token Index: 558