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

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

Neuron 5034 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: 1.1132. Min Range: -1.1132

Max Act: 1.1132. Min Act: -0.0001

Data Index: 1537713 (Python Code)

Max Activating Token Index: 60

Text #1

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.9850. Min Act: -0.0001

Data Index: 1495777 (Python Code)

Max Activating Token Index: 828

Text #2

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.9607. Min Act: -0.0001

Data Index: 1450827 (Python Code)

Max Activating Token Index: 419

Text #3

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.9961. Min Act: -0.0001

Data Index: 1656460 (Python Code)

Max Activating Token Index: 1021

Text #4

Max Range: 1.1132. Min Range: -1.1132

Max Act: 1.0375. Min Act: -0.0001

Data Index: 1601072 (Python Code)

Max Activating Token Index: 149

Text #5

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.9861. Min Act: -0.0001

Data Index: 1654707 (Python Code)

Max Activating Token Index: 853

Text #6

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.8966. Min Act: -0.0001

Data Index: 1534436 (Python Code)

Max Activating Token Index: 856

Text #7

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.8445. Min Act: -0.0001

Data Index: 1550587 (Python Code)

Max Activating Token Index: 161

Text #8

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.8840. Min Act: -0.0001

Data Index: 1461028 (Python Code)

Max Activating Token Index: 46

Text #9

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.9672. Min Act: -0.0001

Data Index: 1544710 (Python Code)

Max Activating Token Index: 978

Text #10

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.8525. Min Act: -0.0001

Data Index: 1570886 (Python Code)

Max Activating Token Index: 582

Text #11

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.9283. Min Act: -0.0001

Data Index: 1260583 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.9069. Min Act: -0.0001

Data Index: 1603297 (Python Code)

Max Activating Token Index: 568

Text #13

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.9539. Min Act: -0.0001

Data Index: 1491049 (Python Code)

Max Activating Token Index: 235

Text #14

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.8652. Min Act: -0.0001

Data Index: 1644610 (Python Code)

Max Activating Token Index: 50

Text #15

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.7975. Min Act: -0.0001

Data Index: 1378658 (Python Code)

Max Activating Token Index: 675

Text #16

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.7154. Min Act: -0.0001

Data Index: 1421501 (Python Code)

Max Activating Token Index: 291

Text #17

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.7577. Min Act: -0.0001

Data Index: 1413514 (Python Code)

Max Activating Token Index: 505

Text #18

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.8053. Min Act: -0.0001

Data Index: 357775 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.7541. Min Act: -0.0001

Data Index: 1409114 (Python Code)

Max Activating Token Index: 243