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

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

Neuron 2317 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: 8.5904. Min Range: -8.5904

Max Act: 8.4211. Min Act: -0.0000

Data Index: 1531009 (Python Code)

Max Activating Token Index: 828

Text #1

Max Range: 8.5904. Min Range: -8.5904

Max Act: 8.4002. Min Act: -0.0000

Data Index: 1625957 (Python Code)

Max Activating Token Index: 966

Text #2

Max Range: 8.5904. Min Range: -8.5904

Max Act: 8.2316. Min Act: -0.0000

Data Index: 1642993 (Python Code)

Max Activating Token Index: 266

Text #3

Max Range: 8.5904. Min Range: -8.5904

Max Act: 8.3848. Min Act: -0.0000

Data Index: 1626890 (Python Code)

Max Activating Token Index: 535

Text #4

Max Range: 8.5904. Min Range: -8.5904

Max Act: 8.3718. Min Act: -0.0000

Data Index: 1596803 (Python Code)

Max Activating Token Index: 237

Text #5

Max Range: 8.5904. Min Range: -8.5904

Max Act: 8.3928. Min Act: -0.0000

Data Index: 1656866 (Python Code)

Max Activating Token Index: 855

Text #6

Max Range: 8.5904. Min Range: -8.5904

Max Act: 8.1385. Min Act: -0.0000

Data Index: 1370073 (Python Code)

Max Activating Token Index: 874

Text #7

Max Range: 8.5904. Min Range: -8.5904

Max Act: 8.5904. Min Act: -0.0000

Data Index: 1512218 (Python Code)

Max Activating Token Index: 907

Text #8

Max Range: 8.5904. Min Range: -8.5904

Max Act: 8.5596. Min Act: -0.0000

Data Index: 1624364 (Python Code)

Max Activating Token Index: 304

Text #9

Max Range: 8.5904. Min Range: -8.5904

Max Act: 8.0680. Min Act: -0.0000

Data Index: 1457062 (Python Code)

Max Activating Token Index: 266

Text #10

Max Range: 8.5904. Min Range: -8.5904

Max Act: 8.3795. Min Act: -0.0000

Data Index: 1504111 (Python Code)

Max Activating Token Index: 527

Text #11

Max Range: 8.5904. Min Range: -8.5904

Max Act: 8.2374. Min Act: -0.0000

Data Index: 1610427 (Python Code)

Max Activating Token Index: 175

Text #12

Max Range: 8.5904. Min Range: -8.5904

Max Act: 8.5263. Min Act: -0.0000

Data Index: 1411418 (Python Code)

Max Activating Token Index: 526

Text #13

Max Range: 8.5904. Min Range: -8.5904

Max Act: 8.3402. Min Act: -0.0000

Data Index: 1429560 (Python Code)

Max Activating Token Index: 744

Text #14

Max Range: 8.5904. Min Range: -8.5904

Max Act: 8.1419. Min Act: -0.0000

Data Index: 1430116 (Python Code)

Max Activating Token Index: 789

Text #15

Max Range: 8.5904. Min Range: -8.5904

Max Act: 8.3048. Min Act: -0.0000

Data Index: 1572442 (Python Code)

Max Activating Token Index: 790

Text #16

Max Range: 8.5904. Min Range: -8.5904

Max Act: 7.9997. Min Act: -0.0000

Data Index: 1651069 (Python Code)

Max Activating Token Index: 937

Text #17

Max Range: 8.5904. Min Range: -8.5904

Max Act: 8.2734. Min Act: -0.0000

Data Index: 1361921 (Python Code)

Max Activating Token Index: 914

Text #18

Max Range: 8.5904. Min Range: -8.5904

Max Act: 7.9367. Min Act: -0.0000

Data Index: 1375130 (Python Code)

Max Activating Token Index: 988

Text #19

Max Range: 8.5904. Min Range: -8.5904

Max Act: 8.0806. Min Act: -0.0000

Data Index: 1596347 (Python Code)

Max Activating Token Index: 449