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

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

Neuron 3705 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0659. Min Range: -2.0659

Max Act: 2.0659. Min Act: -0.0000

Data Index: 925022 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 2.0659. Min Range: -2.0659

Max Act: 2.0639. Min Act: -0.0000

Data Index: 1155110 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 2.0659. Min Range: -2.0659

Max Act: 1.8578. Min Act: -0.0000

Data Index: 807501 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 2.0659. Min Range: -2.0659

Max Act: 1.8538. Min Act: -0.0000

Data Index: 1255926 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 2.0659. Min Range: -2.0659

Max Act: 1.4918. Min Act: -0.0000

Data Index: 103974 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 2.0659. Min Range: -2.0659

Max Act: 1.3768. Min Act: -0.0000

Data Index: 164590 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 2.0659. Min Range: -2.0659

Max Act: 1.4131. Min Act: -0.0000

Data Index: 778522 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 2.0659. Min Range: -2.0659

Max Act: 1.1825. Min Act: -0.0000

Data Index: 592302 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 2.0659. Min Range: -2.0659

Max Act: 1.2192. Min Act: -0.0000

Data Index: 648689 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 2.0659. Min Range: -2.0659

Max Act: 1.2061. Min Act: -0.0000

Data Index: 1302612 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 2.0659. Min Range: -2.0659

Max Act: 1.1766. Min Act: -0.0000

Data Index: 400134 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 2.0659. Min Range: -2.0659

Max Act: 1.1577. Min Act: -0.0000

Data Index: 180966 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 2.0659. Min Range: -2.0659

Max Act: 1.1337. Min Act: -0.0000

Data Index: 678943 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 2.0659. Min Range: -2.0659

Max Act: 1.0573. Min Act: -0.0000

Data Index: 572399 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 2.0659. Min Range: -2.0659

Max Act: 1.1077. Min Act: -0.0000

Data Index: 545512 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 2.0659. Min Range: -2.0659

Max Act: 1.1021. Min Act: -0.0000

Data Index: 552809 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 2.0659. Min Range: -2.0659

Max Act: 1.1446. Min Act: -0.0000

Data Index: 791115 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 2.0659. Min Range: -2.0659

Max Act: 1.0850. Min Act: -0.0000

Data Index: 764779 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 2.0659. Min Range: -2.0659

Max Act: 1.0768. Min Act: -0.0000

Data Index: 1339146 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 2.0659. Min Range: -2.0659

Max Act: 1.0771. Min Act: -0.0000

Data Index: 1009328 (C4 (Web Text))

Max Activating Token Index: 666