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

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

Neuron 4046 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.3840. Min Act: -0.0002

Data Index: 1320746 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.3147. Min Act: -0.0002

Data Index: 457216 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.2809. Min Act: -0.0002

Data Index: 182116 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.1766. Min Act: -0.0002

Data Index: 476805 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.1993. Min Act: -0.0002

Data Index: 145141 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.1837. Min Act: -0.0002

Data Index: 82006 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.1348. Min Act: -0.0002

Data Index: 925940 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.1627. Min Act: -0.0002

Data Index: 402609 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.1330. Min Act: -0.0002

Data Index: 1693 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.1211. Min Act: -0.0002

Data Index: 1014045 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.1449. Min Act: -0.0002

Data Index: 729536 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.1081. Min Act: -0.0002

Data Index: 20205 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.1148. Min Act: -0.0002

Data Index: 826598 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.1089. Min Act: -0.0002

Data Index: 609014 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.1016. Min Act: -0.0002

Data Index: 1329405 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.0899. Min Act: -0.0002

Data Index: 1291001 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.0734. Min Act: -0.0002

Data Index: 1191951 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.0716. Min Act: -0.0002

Data Index: 935070 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.0764. Min Act: -0.0002

Data Index: 466347 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 1.3840. Min Range: -1.3840

Max Act: 1.0678. Min Act: -0.0002

Data Index: 826699 (C4 (Web Text))

Max Activating Token Index: 316