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

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

Neuron 1848 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1895. Min Act: -0.0001

Data Index: 1312300 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1968. Min Act: -0.0001

Data Index: 1124583 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1916. Min Act: -0.0001

Data Index: 174255 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1759. Min Act: -0.0001

Data Index: 151105 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1768. Min Act: -0.0001

Data Index: 909516 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1724. Min Act: -0.0001

Data Index: 423631 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1722. Min Act: -0.0001

Data Index: 31307 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1801. Min Act: -0.0001

Data Index: 173245 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1683. Min Act: -0.0000

Data Index: 611180 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1210160 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1671. Min Act: -0.0001

Data Index: 90154 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1600. Min Act: -0.0000

Data Index: 11986 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1597. Min Act: -0.0001

Data Index: 793130 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1636. Min Act: -0.0001

Data Index: 297591 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1697. Min Act: -0.0001

Data Index: 715583 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1272091 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1624. Min Act: -0.0001

Data Index: 477107 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1550. Min Act: -0.0001

Data Index: 896877 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1660. Min Act: -0.0001

Data Index: 524060 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1600. Min Act: -0.0000

Data Index: 1181161 (C4 (Web Text))

Max Activating Token Index: 171