Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2842 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.6910. Min Act: -0.0000

Data Index: 1390569 (Python Code)

Max Activating Token Index: 751

Text #1

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1371545 (Python Code)

Max Activating Token Index: 840

Text #2

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1370449 (Python Code)

Max Activating Token Index: 263

Text #3

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1649018 (Python Code)

Max Activating Token Index: 776

Text #4

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.6309. Min Act: -0.0000

Data Index: 1415237 (Python Code)

Max Activating Token Index: 404

Text #5

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1599029 (Python Code)

Max Activating Token Index: 122

Text #6

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1487243 (Python Code)

Max Activating Token Index: 737

Text #7

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1581186 (Python Code)

Max Activating Token Index: 588

Text #8

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5408. Min Act: -0.0000

Data Index: 1591604 (Python Code)

Max Activating Token Index: 748

Text #9

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1367647 (Python Code)

Max Activating Token Index: 852

Text #10

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1391613 (Python Code)

Max Activating Token Index: 752

Text #11

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1574967 (Python Code)

Max Activating Token Index: 856

Text #12

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1587444 (Python Code)

Max Activating Token Index: 351

Text #13

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4646. Min Act: -0.0000

Data Index: 1469430 (Python Code)

Max Activating Token Index: 88

Text #14

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4299. Min Act: -0.0000

Data Index: 1602259 (Python Code)

Max Activating Token Index: 308

Text #15

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4424. Min Act: -0.0000

Data Index: 1461813 (Python Code)

Max Activating Token Index: 879

Text #16

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1509119 (Python Code)

Max Activating Token Index: 697

Text #17

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4359. Min Act: -0.0000

Data Index: 1577147 (Python Code)

Max Activating Token Index: 597

Text #18

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1453934 (Python Code)

Max Activating Token Index: 912

Text #19

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1516358 (Python Code)

Max Activating Token Index: 857