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

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

Neuron 4583 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1921. Min Range: -3.1921

Max Act: 3.0300. Min Act: -0.0000

Data Index: 796118 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 3.1921. Min Range: -3.1921

Max Act: 3.0665. Min Act: -0.0000

Data Index: 775962 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 3.1921. Min Range: -3.1921

Max Act: 3.1921. Min Act: -0.0000

Data Index: 724417 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 3.1921. Min Range: -3.1921

Max Act: 2.9475. Min Act: -0.0000

Data Index: 736616 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 3.1921. Min Range: -3.1921

Max Act: 3.0402. Min Act: -0.0000

Data Index: 673995 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 3.1921. Min Range: -3.1921

Max Act: 2.9014. Min Act: -0.0000

Data Index: 412944 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 3.1921. Min Range: -3.1921

Max Act: 2.6777. Min Act: -0.0000

Data Index: 806597 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 3.1921. Min Range: -3.1921

Max Act: 2.6176. Min Act: -0.0000

Data Index: 774933 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 3.1921. Min Range: -3.1921

Max Act: 2.7928. Min Act: -0.0000

Data Index: 718809 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 3.1921. Min Range: -3.1921

Max Act: 2.7626. Min Act: -0.0000

Data Index: 1192771 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 3.1921. Min Range: -3.1921

Max Act: 2.7055. Min Act: -0.0000

Data Index: 18330 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 3.1921. Min Range: -3.1921

Max Act: 2.2986. Min Act: -0.0000

Data Index: 734101 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 3.1921. Min Range: -3.1921

Max Act: 2.0887. Min Act: -0.0000

Data Index: 144497 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 3.1921. Min Range: -3.1921

Max Act: 2.0763. Min Act: -0.0000

Data Index: 770946 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 3.1921. Min Range: -3.1921

Max Act: 2.0497. Min Act: -0.0000

Data Index: 384971 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 3.1921. Min Range: -3.1921

Max Act: 2.0459. Min Act: -0.0000

Data Index: 498767 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 3.1921. Min Range: -3.1921

Max Act: 2.1215. Min Act: -0.0000

Data Index: 229190 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 3.1921. Min Range: -3.1921

Max Act: 1.8906. Min Act: -0.0000

Data Index: 544824 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 3.1921. Min Range: -3.1921

Max Act: 1.9950. Min Act: -0.0000

Data Index: 289985 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 3.1921. Min Range: -3.1921

Max Act: 2.0248. Min Act: -0.0000

Data Index: 630188 (C4 (Web Text))

Max Activating Token Index: 714