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

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

Neuron 6104 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.3777. Min Act: -0.0000

Data Index: 1516025 (Python Code)

Max Activating Token Index: 768

Text #1

Max Range: 4.3777. Min Range: -4.3777

Max Act: 3.9359. Min Act: -0.0000

Data Index: 1499593 (Python Code)

Max Activating Token Index: 975

Text #2

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.0750. Min Act: -0.0000

Data Index: 1597027 (Python Code)

Max Activating Token Index: 521

Text #3

Max Range: 4.3777. Min Range: -4.3777

Max Act: 3.9278. Min Act: -0.0000

Data Index: 1411179 (Python Code)

Max Activating Token Index: 840

Text #4

Max Range: 4.3777. Min Range: -4.3777

Max Act: 3.8609. Min Act: -0.0000

Data Index: 1445131 (Python Code)

Max Activating Token Index: 862

Text #5

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.1867. Min Act: -0.0000

Data Index: 1552907 (Python Code)

Max Activating Token Index: 615

Text #6

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.2722. Min Act: -0.0000

Data Index: 1455776 (Python Code)

Max Activating Token Index: 642

Text #7

Max Range: 4.3777. Min Range: -4.3777

Max Act: 3.8347. Min Act: -0.0000

Data Index: 1652922 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 4.3777. Min Range: -4.3777

Max Act: 3.7442. Min Act: -0.0000

Data Index: 1566128 (Python Code)

Max Activating Token Index: 476

Text #9

Max Range: 4.3777. Min Range: -4.3777

Max Act: 3.7812. Min Act: -0.0000

Data Index: 1375366 (Python Code)

Max Activating Token Index: 278

Text #10

Max Range: 4.3777. Min Range: -4.3777

Max Act: 3.6524. Min Act: -0.0000

Data Index: 1536144 (Python Code)

Max Activating Token Index: 842

Text #11

Max Range: 4.3777. Min Range: -4.3777

Max Act: 3.3875. Min Act: -0.0000

Data Index: 1485800 (Python Code)

Max Activating Token Index: 383

Text #12

Max Range: 4.3777. Min Range: -4.3777

Max Act: 3.3405. Min Act: -0.0000

Data Index: 1504475 (Python Code)

Max Activating Token Index: 381

Text #13

Max Range: 4.3777. Min Range: -4.3777

Max Act: 3.6637. Min Act: -0.0000

Data Index: 1607916 (Python Code)

Max Activating Token Index: 940

Text #14

Max Range: 4.3777. Min Range: -4.3777

Max Act: 3.3059. Min Act: -0.0000

Data Index: 1533744 (Python Code)

Max Activating Token Index: 586

Text #15

Max Range: 4.3777. Min Range: -4.3777

Max Act: 3.4484. Min Act: -0.0000

Data Index: 1475924 (Python Code)

Max Activating Token Index: 594

Text #16

Max Range: 4.3777. Min Range: -4.3777

Max Act: 3.4271. Min Act: -0.0000

Data Index: 1595768 (Python Code)

Max Activating Token Index: 71

Text #17

Max Range: 4.3777. Min Range: -4.3777

Max Act: 3.4154. Min Act: -0.0000

Data Index: 1512483 (Python Code)

Max Activating Token Index: 921

Text #18

Max Range: 4.3777. Min Range: -4.3777

Max Act: 3.1949. Min Act: -0.0000

Data Index: 1501477 (Python Code)

Max Activating Token Index: 500

Text #19

Max Range: 4.3777. Min Range: -4.3777

Max Act: 3.3588. Min Act: -0.0000

Data Index: 1465357 (Python Code)

Max Activating Token Index: 889