Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 224 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1915. Min Act: -0.0001

Data Index: 1032857 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1845. Min Act: -0.0001

Data Index: 771748 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1551. Min Act: -0.0001

Data Index: 988128 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1754. Min Act: -0.0001

Data Index: 675616 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1739. Min Act: -0.0001

Data Index: 1253638 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1760. Min Act: -0.0001

Data Index: 68174 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1785. Min Act: -0.0001

Data Index: 1212555 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1916. Min Act: -0.0001

Data Index: 708803 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1792. Min Act: -0.0001

Data Index: 1044316 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1768. Min Act: -0.0001

Data Index: 242085 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1770. Min Act: -0.0001

Data Index: 755217 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1687. Min Act: -0.0001

Data Index: 1228811 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1620. Min Act: -0.0001

Data Index: 518759 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1681. Min Act: -0.0001

Data Index: 1203867 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1588. Min Act: -0.0001

Data Index: 431061 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1744. Min Act: -0.0001

Data Index: 1336468 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1842. Min Act: -0.0001

Data Index: 811801 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1960. Min Act: -0.0001

Data Index: 974155 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1694. Min Act: -0.0001

Data Index: 1052616 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1637. Min Act: -0.0001

Data Index: 1109689 (C4 (Web Text))

Max Activating Token Index: 168