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

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

Neuron 4507 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1927. Min Act: -0.0000

Data Index: 725759 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1826. Min Act: -0.0001

Data Index: 772205 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1878. Min Act: -0.0001

Data Index: 960199 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1889. Min Act: -0.0000

Data Index: 1262628 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1605. Min Act: -0.0000

Data Index: 827878 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1579. Min Act: -0.0001

Data Index: 940221 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1741. Min Act: -0.0000

Data Index: 67346 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1524. Min Act: -0.0000

Data Index: 779936 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1396. Min Act: -0.0000

Data Index: 1421494 (Python Code)

Max Activating Token Index: 127

Text #9

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1149. Min Act: -0.0000

Data Index: 1461540 (Python Code)

Max Activating Token Index: 45

Text #10

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1129. Min Act: -0.0000

Data Index: 932282 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1174. Min Act: -0.0000

Data Index: 108121 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1077. Min Act: -0.0000

Data Index: 1416887 (Python Code)

Max Activating Token Index: 682

Text #13

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1094. Min Act: -0.0000

Data Index: 548246 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.0867. Min Act: -0.0000

Data Index: 884448 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1587199 (Python Code)

Max Activating Token Index: 606

Text #16

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1095. Min Act: -0.0000

Data Index: 1478543 (Python Code)

Max Activating Token Index: 348

Text #17

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1461524 (Python Code)

Max Activating Token Index: 502

Text #18

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.0949. Min Act: -0.0000

Data Index: 1588040 (Python Code)

Max Activating Token Index: 833

Text #19

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1368691 (Python Code)

Max Activating Token Index: 225