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

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

Neuron 1912 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.5618. Min Act: -0.0000

Data Index: 909223 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.5044. Min Act: -0.0000

Data Index: 1523254 (Python Code)

Max Activating Token Index: 444

Text #2

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.3405. Min Act: -0.0000

Data Index: 1442171 (Python Code)

Max Activating Token Index: 916

Text #3

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.2948. Min Act: -0.0000

Data Index: 1362528 (Python Code)

Max Activating Token Index: 658

Text #4

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.3786. Min Act: -0.0000

Data Index: 1437350 (Python Code)

Max Activating Token Index: 72

Text #5

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.2854. Min Act: -0.0000

Data Index: 1433851 (Python Code)

Max Activating Token Index: 151

Text #6

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.2922. Min Act: -0.0001

Data Index: 1412923 (Python Code)

Max Activating Token Index: 11

Text #7

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.3572. Min Act: -0.0000

Data Index: 1391782 (Python Code)

Max Activating Token Index: 376

Text #8

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.2859. Min Act: -0.0000

Data Index: 1446003 (Python Code)

Max Activating Token Index: 123

Text #9

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.2331. Min Act: -0.0000

Data Index: 1637051 (Python Code)

Max Activating Token Index: 552

Text #10

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.2649. Min Act: -0.0000

Data Index: 1443319 (Python Code)

Max Activating Token Index: 49

Text #11

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.2078. Min Act: -0.0000

Data Index: 1585220 (Python Code)

Max Activating Token Index: 920

Text #12

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.3213. Min Act: -0.0000

Data Index: 301825 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.2410. Min Act: -0.0000

Data Index: 1371383 (Python Code)

Max Activating Token Index: 5

Text #14

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.2065. Min Act: -0.0000

Data Index: 1650772 (Python Code)

Max Activating Token Index: 71

Text #15

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.2709. Min Act: -0.0000

Data Index: 1416726 (Python Code)

Max Activating Token Index: 527

Text #16

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.2749. Min Act: -0.0000

Data Index: 1591606 (Python Code)

Max Activating Token Index: 103

Text #17

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.2662. Min Act: -0.0000

Data Index: 1641511 (Python Code)

Max Activating Token Index: 404

Text #18

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.3006. Min Act: -0.0000

Data Index: 1402684 (Python Code)

Max Activating Token Index: 190

Text #19

Max Range: 1.5618. Min Range: -1.5618

Max Act: 1.2593. Min Act: -0.0000

Data Index: 1407847 (Python Code)

Max Activating Token Index: 26