Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4228 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2865. Min Act: -0.0000

Data Index: 301244 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2141. Min Act: -0.0000

Data Index: 518576 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1953. Min Act: -0.0000

Data Index: 259600 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1918. Min Act: -0.0000

Data Index: 524720 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1764. Min Act: -0.0001

Data Index: 931700 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1787. Min Act: -0.0000

Data Index: 652011 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1192127 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1720. Min Act: -0.0001

Data Index: 464976 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1123602 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1656. Min Act: -0.0000

Data Index: 20331 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1742. Min Act: -0.0001

Data Index: 1252279 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1632. Min Act: -0.0001

Data Index: 99086 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1566. Min Act: -0.0001

Data Index: 646942 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1661. Min Act: -0.0001

Data Index: 198916 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1520. Min Act: -0.0000

Data Index: 505104 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1562. Min Act: -0.0001

Data Index: 530277 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1483. Min Act: -0.0001

Data Index: 145039 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1544. Min Act: -0.0001

Data Index: 567683 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1414. Min Act: -0.0000

Data Index: 839120 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1466. Min Act: -0.0000

Data Index: 517275 (C4 (Web Text))

Max Activating Token Index: 884