Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5010 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.7339. Min Range: -3.7339

Max Act: 3.7339. Min Act: -0.0000

Data Index: 1170956 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 3.7339. Min Range: -3.7339

Max Act: 3.2667. Min Act: -0.0000

Data Index: 686916 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 3.7339. Min Range: -3.7339

Max Act: 3.1915. Min Act: -0.0000

Data Index: 689413 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 3.7339. Min Range: -3.7339

Max Act: 2.8635. Min Act: -0.0000

Data Index: 827579 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 3.7339. Min Range: -3.7339

Max Act: 3.0253. Min Act: -0.0000

Data Index: 1307021 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 3.7339. Min Range: -3.7339

Max Act: 2.9434. Min Act: -0.0000

Data Index: 8540 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 3.7339. Min Range: -3.7339

Max Act: 2.8064. Min Act: -0.0000

Data Index: 1001985 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 3.7339. Min Range: -3.7339

Max Act: 2.7582. Min Act: -0.0000

Data Index: 1213055 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 3.7339. Min Range: -3.7339

Max Act: 2.8898. Min Act: -0.0000

Data Index: 1209537 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 3.7339. Min Range: -3.7339

Max Act: 2.9758. Min Act: -0.0000

Data Index: 1179137 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 3.7339. Min Range: -3.7339

Max Act: 2.6033. Min Act: -0.0000

Data Index: 1314838 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 3.7339. Min Range: -3.7339

Max Act: 2.7376. Min Act: -0.0000

Data Index: 439289 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 3.7339. Min Range: -3.7339

Max Act: 2.6049. Min Act: -0.0000

Data Index: 771292 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 3.7339. Min Range: -3.7339

Max Act: 2.5605. Min Act: -0.0000

Data Index: 589032 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 3.7339. Min Range: -3.7339

Max Act: 2.5492. Min Act: -0.0000

Data Index: 1116655 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 3.7339. Min Range: -3.7339

Max Act: 2.5754. Min Act: -0.0000

Data Index: 1107555 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 3.7339. Min Range: -3.7339

Max Act: 2.5514. Min Act: -0.0000

Data Index: 183481 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 3.7339. Min Range: -3.7339

Max Act: 2.4943. Min Act: -0.0000

Data Index: 409979 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 3.7339. Min Range: -3.7339

Max Act: 2.5687. Min Act: -0.0000

Data Index: 406292 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 3.7339. Min Range: -3.7339

Max Act: 2.5323. Min Act: -0.0000

Data Index: 695561 (C4 (Web Text))

Max Activating Token Index: 37