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

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

Neuron 1658 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1951. Min Act: -0.0000

Data Index: 215884 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1201836 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1942. Min Act: -0.0000

Data Index: 536301 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1924. Min Act: -0.0000

Data Index: 782466 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1839. Min Act: -0.0000

Data Index: 46354 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1046407 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1724. Min Act: -0.0000

Data Index: 173894 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1911. Min Act: -0.0000

Data Index: 890182 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1729. Min Act: -0.0000

Data Index: 240486 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1737. Min Act: -0.0000

Data Index: 964878 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1669. Min Act: -0.0000

Data Index: 687029 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1706. Min Act: -0.0000

Data Index: 487330 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1710. Min Act: -0.0000

Data Index: 11910 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1722. Min Act: -0.0000

Data Index: 45713 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1683. Min Act: -0.0000

Data Index: 500742 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1684. Min Act: -0.0000

Data Index: 1258103 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1084391 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1651. Min Act: -0.0000

Data Index: 308630 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1645. Min Act: -0.0000

Data Index: 298128 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1593. Min Act: -0.0000

Data Index: 152297 (C4 (Web Text))

Max Activating Token Index: 332