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

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

Neuron 4268 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.2183. Min Act: -0.0000

Data Index: 385142 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.2044. Min Act: -0.0000

Data Index: 1892 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1867. Min Act: -0.0000

Data Index: 874583 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1794. Min Act: -0.0000

Data Index: 400861 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1725. Min Act: -0.0000

Data Index: 974232 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1554. Min Act: -0.0000

Data Index: 1121443 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1603. Min Act: -0.0000

Data Index: 137126 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1637. Min Act: -0.0000

Data Index: 999179 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1642. Min Act: -0.0000

Data Index: 1285706 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1631. Min Act: -0.0000

Data Index: 573410 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1691. Min Act: -0.0000

Data Index: 619237 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1629. Min Act: -0.0000

Data Index: 521232 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1288255 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1561. Min Act: -0.0000

Data Index: 1200252 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1606. Min Act: -0.0000

Data Index: 825155 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1305381 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1199650 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1162383 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1538. Min Act: -0.0000

Data Index: 970771 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1629. Min Act: -0.0000

Data Index: 1089825 (C4 (Web Text))

Max Activating Token Index: 202