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

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

Neuron 4049 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2919. Min Range: -7.2919

Max Act: 7.2919. Min Act: -0.0000

Data Index: 1625979 (Python Code)

Max Activating Token Index: 956

Text #1

Max Range: 7.2919. Min Range: -7.2919

Max Act: 6.2232. Min Act: -0.0000

Data Index: 1381710 (Python Code)

Max Activating Token Index: 197

Text #2

Max Range: 7.2919. Min Range: -7.2919

Max Act: 5.8645. Min Act: -0.0000

Data Index: 1528151 (Python Code)

Max Activating Token Index: 383

Text #3

Max Range: 7.2919. Min Range: -7.2919

Max Act: 5.4559. Min Act: -0.0000

Data Index: 1497738 (Python Code)

Max Activating Token Index: 979

Text #4

Max Range: 7.2919. Min Range: -7.2919

Max Act: 5.4868. Min Act: -0.0000

Data Index: 1390474 (Python Code)

Max Activating Token Index: 456

Text #5

Max Range: 7.2919. Min Range: -7.2919

Max Act: 5.2079. Min Act: -0.0000

Data Index: 1619293 (Python Code)

Max Activating Token Index: 148

Text #6

Max Range: 7.2919. Min Range: -7.2919

Max Act: 5.1958. Min Act: -0.0000

Data Index: 1621089 (Python Code)

Max Activating Token Index: 880

Text #7

Max Range: 7.2919. Min Range: -7.2919

Max Act: 4.9757. Min Act: -0.0000

Data Index: 1544440 (Python Code)

Max Activating Token Index: 771

Text #8

Max Range: 7.2919. Min Range: -7.2919

Max Act: 4.6319. Min Act: -0.0000

Data Index: 1552849 (Python Code)

Max Activating Token Index: 641

Text #9

Max Range: 7.2919. Min Range: -7.2919

Max Act: 4.7269. Min Act: -0.0000

Data Index: 1582570 (Python Code)

Max Activating Token Index: 942

Text #10

Max Range: 7.2919. Min Range: -7.2919

Max Act: 4.9745. Min Act: -0.0000

Data Index: 1383305 (Python Code)

Max Activating Token Index: 794

Text #11

Max Range: 7.2919. Min Range: -7.2919

Max Act: 4.7520. Min Act: -0.0000

Data Index: 1545498 (Python Code)

Max Activating Token Index: 677

Text #12

Max Range: 7.2919. Min Range: -7.2919

Max Act: 4.3804. Min Act: -0.0000

Data Index: 1472618 (Python Code)

Max Activating Token Index: 351

Text #13

Max Range: 7.2919. Min Range: -7.2919

Max Act: 4.4318. Min Act: -0.0000

Data Index: 1486967 (Python Code)

Max Activating Token Index: 371

Text #14

Max Range: 7.2919. Min Range: -7.2919

Max Act: 4.0049. Min Act: -0.0000

Data Index: 1492770 (Python Code)

Max Activating Token Index: 759

Text #15

Max Range: 7.2919. Min Range: -7.2919

Max Act: 4.5515. Min Act: -0.0000

Data Index: 1654435 (Python Code)

Max Activating Token Index: 368

Text #16

Max Range: 7.2919. Min Range: -7.2919

Max Act: 4.1742. Min Act: -0.0000

Data Index: 1595330 (Python Code)

Max Activating Token Index: 406

Text #17

Max Range: 7.2919. Min Range: -7.2919

Max Act: 4.1443. Min Act: -0.0000

Data Index: 1527336 (Python Code)

Max Activating Token Index: 79

Text #18

Max Range: 7.2919. Min Range: -7.2919

Max Act: 3.9418. Min Act: -0.0000

Data Index: 1393762 (Python Code)

Max Activating Token Index: 104

Text #19

Max Range: 7.2919. Min Range: -7.2919

Max Act: 4.2360. Min Act: -0.0000

Data Index: 1383637 (Python Code)

Max Activating Token Index: 541