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

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

Neuron 1515 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0470. Min Range: -2.0470

Max Act: 2.0470. Min Act: -0.0000

Data Index: 289794 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 2.0470. Min Range: -2.0470

Max Act: 1.9104. Min Act: -0.0000

Data Index: 61548 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 2.0470. Min Range: -2.0470

Max Act: 1.8103. Min Act: -0.0000

Data Index: 727969 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 2.0470. Min Range: -2.0470

Max Act: 1.4708. Min Act: -0.0000

Data Index: 1203230 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 2.0470. Min Range: -2.0470

Max Act: 1.2685. Min Act: -0.0000

Data Index: 46006 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 2.0470. Min Range: -2.0470

Max Act: 1.2643. Min Act: -0.0000

Data Index: 1014577 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 2.0470. Min Range: -2.0470

Max Act: 1.2131. Min Act: -0.0000

Data Index: 577856 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 2.0470. Min Range: -2.0470

Max Act: 1.1727. Min Act: -0.0000

Data Index: 849276 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 2.0470. Min Range: -2.0470

Max Act: 1.2013. Min Act: -0.0000

Data Index: 917330 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 2.0470. Min Range: -2.0470

Max Act: 1.1065. Min Act: -0.0000

Data Index: 353116 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 2.0470. Min Range: -2.0470

Max Act: 1.1566. Min Act: -0.0000

Data Index: 139248 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 2.0470. Min Range: -2.0470

Max Act: 1.0577. Min Act: -0.0000

Data Index: 1184688 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 2.0470. Min Range: -2.0470

Max Act: 1.1876. Min Act: -0.0000

Data Index: 47388 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 2.0470. Min Range: -2.0470

Max Act: 1.0777. Min Act: -0.0000

Data Index: 349538 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 2.0470. Min Range: -2.0470

Max Act: 1.0491. Min Act: -0.0000

Data Index: 147541 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 2.0470. Min Range: -2.0470

Max Act: 0.9137. Min Act: -0.0000

Data Index: 79730 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 2.0470. Min Range: -2.0470

Max Act: 0.9483. Min Act: -0.0000

Data Index: 547965 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 2.0470. Min Range: -2.0470

Max Act: 1.0474. Min Act: -0.0000

Data Index: 1284652 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 2.0470. Min Range: -2.0470

Max Act: 0.9614. Min Act: -0.0000

Data Index: 1338188 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 2.0470. Min Range: -2.0470

Max Act: 0.9531. Min Act: -0.0000

Data Index: 652513 (C4 (Web Text))

Max Activating Token Index: 473