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

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

Neuron 2510 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: 4.8875. Min Range: -4.8875

Max Act: 4.8875. Min Act: -0.0000

Data Index: 1522603 (Python Code)

Max Activating Token Index: 967

Text #1

Max Range: 4.8875. Min Range: -4.8875

Max Act: 4.6994. Min Act: -0.0000

Data Index: 153730 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 4.8875. Min Range: -4.8875

Max Act: 4.2070. Min Act: -0.0000

Data Index: 1429697 (Python Code)

Max Activating Token Index: 535

Text #3

Max Range: 4.8875. Min Range: -4.8875

Max Act: 4.1943. Min Act: -0.0000

Data Index: 1583997 (Python Code)

Max Activating Token Index: 121

Text #4

Max Range: 4.8875. Min Range: -4.8875

Max Act: 4.0011. Min Act: -0.0000

Data Index: 1613982 (Python Code)

Max Activating Token Index: 690

Text #5

Max Range: 4.8875. Min Range: -4.8875

Max Act: 3.7546. Min Act: -0.0000

Data Index: 1436274 (Python Code)

Max Activating Token Index: 59

Text #6

Max Range: 4.8875. Min Range: -4.8875

Max Act: 3.6084. Min Act: -0.0000

Data Index: 1462959 (Python Code)

Max Activating Token Index: 812

Text #7

Max Range: 4.8875. Min Range: -4.8875

Max Act: 3.7468. Min Act: -0.0000

Data Index: 1458340 (Python Code)

Max Activating Token Index: 240

Text #8

Max Range: 4.8875. Min Range: -4.8875

Max Act: 3.7370. Min Act: -0.0000

Data Index: 1417567 (Python Code)

Max Activating Token Index: 704

Text #9

Max Range: 4.8875. Min Range: -4.8875

Max Act: 3.8504. Min Act: -0.0000

Data Index: 1501998 (Python Code)

Max Activating Token Index: 125

Text #10

Max Range: 4.8875. Min Range: -4.8875

Max Act: 3.8139. Min Act: -0.0000

Data Index: 1408433 (Python Code)

Max Activating Token Index: 560

Text #11

Max Range: 4.8875. Min Range: -4.8875

Max Act: 3.7653. Min Act: -0.0000

Data Index: 1564337 (Python Code)

Max Activating Token Index: 623

Text #12

Max Range: 4.8875. Min Range: -4.8875

Max Act: 3.7252. Min Act: -0.0000

Data Index: 1500162 (Python Code)

Max Activating Token Index: 681

Text #13

Max Range: 4.8875. Min Range: -4.8875

Max Act: 4.0324. Min Act: -0.0000

Data Index: 1538592 (Python Code)

Max Activating Token Index: 773

Text #14

Max Range: 4.8875. Min Range: -4.8875

Max Act: 3.5660. Min Act: -0.0000

Data Index: 1489787 (Python Code)

Max Activating Token Index: 401

Text #15

Max Range: 4.8875. Min Range: -4.8875

Max Act: 3.8758. Min Act: -0.0000

Data Index: 1526772 (Python Code)

Max Activating Token Index: 798

Text #16

Max Range: 4.8875. Min Range: -4.8875

Max Act: 3.6659. Min Act: -0.0000

Data Index: 1429185 (Python Code)

Max Activating Token Index: 480

Text #17

Max Range: 4.8875. Min Range: -4.8875

Max Act: 3.4623. Min Act: -0.0000

Data Index: 1611320 (Python Code)

Max Activating Token Index: 366

Text #18

Max Range: 4.8875. Min Range: -4.8875

Max Act: 3.5861. Min Act: -0.0000

Data Index: 1570249 (Python Code)

Max Activating Token Index: 449

Text #19

Max Range: 4.8875. Min Range: -4.8875

Max Act: 3.3905. Min Act: -0.0000

Data Index: 1555935 (Python Code)

Max Activating Token Index: 521