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

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

Neuron 3977 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.8917. Min Act: -0.0000

Data Index: 1188428 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 4.0278. Min Range: -4.0278

Max Act: 4.0278. Min Act: -0.0000

Data Index: 275319 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.6651. Min Act: -0.0001

Data Index: 753621 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.6500. Min Act: -0.0001

Data Index: 884398 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.7624. Min Act: -0.0000

Data Index: 1355317 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.9065. Min Act: -0.0000

Data Index: 264000 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.9023. Min Act: -0.0000

Data Index: 951532 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.6734. Min Act: -0.0001

Data Index: 661718 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.6496. Min Act: -0.0001

Data Index: 1128437 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.6199. Min Act: -0.0000

Data Index: 724423 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.4643. Min Act: -0.0000

Data Index: 909420 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.7417. Min Act: -0.0000

Data Index: 119633 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.2018. Min Act: -0.0001

Data Index: 424325 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.4792. Min Act: -0.0000

Data Index: 461584 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.3109. Min Act: -0.0001

Data Index: 547347 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.6186. Min Act: -0.0000

Data Index: 448031 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.4393. Min Act: -0.0000

Data Index: 867093 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.2583. Min Act: -0.0000

Data Index: 344871 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.4193. Min Act: -0.0000

Data Index: 886938 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 4.0278. Min Range: -4.0278

Max Act: 3.4021. Min Act: -0.0000

Data Index: 906545 (C4 (Web Text))

Max Activating Token Index: 168