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

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

Neuron 5864 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0525. Min Range: -4.0525

Max Act: 4.0525. Min Act: -0.0000

Data Index: 222831 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.7802. Min Act: -0.0000

Data Index: 931422 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.5085. Min Act: -0.0000

Data Index: 949960 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.5340. Min Act: -0.0000

Data Index: 946172 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.2480. Min Act: -0.0000

Data Index: 1113721 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.3385. Min Act: -0.0000

Data Index: 573784 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.2377. Min Act: -0.0000

Data Index: 137597 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.2209. Min Act: -0.0000

Data Index: 82080 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.2202. Min Act: -0.0000

Data Index: 634649 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.1809. Min Act: -0.0000

Data Index: 1140265 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.4608. Min Act: -0.0000

Data Index: 131453 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.1348. Min Act: -0.0000

Data Index: 1056592 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.3043. Min Act: -0.0000

Data Index: 735219 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 4.0525. Min Range: -4.0525

Max Act: 2.9791. Min Act: -0.0000

Data Index: 1109528 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.0631. Min Act: -0.0000

Data Index: 1279659 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 4.0525. Min Range: -4.0525

Max Act: 2.7995. Min Act: -0.0000

Data Index: 977055 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.0362. Min Act: -0.0000

Data Index: 1338905 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 4.0525. Min Range: -4.0525

Max Act: 2.8042. Min Act: -0.0000

Data Index: 117797 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 4.0525. Min Range: -4.0525

Max Act: 2.7830. Min Act: -0.0000

Data Index: 539660 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 4.0525. Min Range: -4.0525

Max Act: 2.8810. Min Act: -0.0000

Data Index: 829570 (C4 (Web Text))

Max Activating Token Index: 148