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

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

Neuron 5150 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: 2.0938. Min Range: -2.0938

Max Act: 1.8813. Min Act: -0.0000

Data Index: 1603902 (Python Code)

Max Activating Token Index: 973

Text #1

Max Range: 2.0938. Min Range: -2.0938

Max Act: 2.0938. Min Act: -0.0000

Data Index: 1562958 (Python Code)

Max Activating Token Index: 40

Text #2

Max Range: 2.0938. Min Range: -2.0938

Max Act: 2.0787. Min Act: -0.0000

Data Index: 1540047 (Python Code)

Max Activating Token Index: 525

Text #3

Max Range: 2.0938. Min Range: -2.0938

Max Act: 2.0729. Min Act: -0.0000

Data Index: 1606559 (Python Code)

Max Activating Token Index: 912

Text #4

Max Range: 2.0938. Min Range: -2.0938

Max Act: 2.0627. Min Act: -0.0000

Data Index: 1499719 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.9411. Min Act: -0.0000

Data Index: 1510097 (Python Code)

Max Activating Token Index: 106

Text #6

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.8153. Min Act: -0.0000

Data Index: 1464518 (Python Code)

Max Activating Token Index: 617

Text #7

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.7930. Min Act: -0.0000

Data Index: 907678 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.9976. Min Act: -0.0000

Data Index: 1656893 (Python Code)

Max Activating Token Index: 214

Text #9

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.7748. Min Act: -0.0000

Data Index: 1383747 (Python Code)

Max Activating Token Index: 134

Text #10

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.9657. Min Act: -0.0000

Data Index: 1561497 (Python Code)

Max Activating Token Index: 82

Text #11

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.7407. Min Act: -0.0000

Data Index: 206512 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.7423. Min Act: -0.0000

Data Index: 1629635 (Python Code)

Max Activating Token Index: 361

Text #13

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.8091. Min Act: -0.0000

Data Index: 1529557 (Python Code)

Max Activating Token Index: 508

Text #14

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.8042. Min Act: -0.0000

Data Index: 1405923 (Python Code)

Max Activating Token Index: 353

Text #15

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.8131. Min Act: -0.0000

Data Index: 1629895 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.7994. Min Act: -0.0000

Data Index: 1459918 (Python Code)

Max Activating Token Index: 15

Text #17

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.8823. Min Act: -0.0000

Data Index: 1521637 (Python Code)

Max Activating Token Index: 21

Text #18

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.7778. Min Act: -0.0000

Data Index: 1626515 (Python Code)

Max Activating Token Index: 393

Text #19

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.8794. Min Act: -0.0000

Data Index: 470023 (C4 (Web Text))

Max Activating Token Index: 8