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

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

Neuron 3232 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.5811. Min Act: -0.0000

Data Index: 520913 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.5048. Min Act: -0.0000

Data Index: 645773 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4512. Min Act: -0.0000

Data Index: 1083683 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4149. Min Act: -0.0000

Data Index: 599658 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4085. Min Act: -0.0000

Data Index: 83810 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4062. Min Act: -0.0000

Data Index: 459506 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4144. Min Act: -0.0000

Data Index: 88956 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4094. Min Act: -0.0000

Data Index: 901835 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1232372 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4239. Min Act: -0.0000

Data Index: 77774 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4168. Min Act: -0.0000

Data Index: 1038235 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4346. Min Act: -0.0000

Data Index: 1224462 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3843. Min Act: -0.0000

Data Index: 1035143 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1284514 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1271128 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1341612 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.4061. Min Act: -0.0000

Data Index: 1141001 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3798. Min Act: -0.0000

Data Index: 597887 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3822. Min Act: -0.0000

Data Index: 1182990 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.5811. Min Range: -0.5811

Max Act: 0.3887. Min Act: -0.0000

Data Index: 103250 (C4 (Web Text))

Max Activating Token Index: 320