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

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

Neuron 2371 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: 0.4617. Min Range: -0.4617

Max Act: 0.4617. Min Act: -0.0000

Data Index: 892327 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.4509. Min Act: -0.0000

Data Index: 32220 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.4368. Min Act: -0.0000

Data Index: 404954 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.4368. Min Act: -0.0000

Data Index: 29454 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.4492. Min Act: 0.0000

Data Index: 819658 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1339444 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3897. Min Act: -0.0000

Data Index: 70751 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.4190. Min Act: -0.0000

Data Index: 532612 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.4064. Min Act: -0.0000

Data Index: 360099 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3706. Min Act: -0.0000

Data Index: 675538 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3711. Min Act: -0.0000

Data Index: 1152990 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3877. Min Act: -0.0000

Data Index: 117635 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3989. Min Act: 0.0001

Data Index: 73724 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3827. Min Act: 0.0000

Data Index: 275833 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3669. Min Act: -0.0000

Data Index: 1015870 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3720. Min Act: -0.0000

Data Index: 537512 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1300002 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3778. Min Act: -0.0000

Data Index: 720291 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3694. Min Act: -0.0000

Data Index: 384271 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3726. Min Act: -0.0000

Data Index: 206802 (C4 (Web Text))

Max Activating Token Index: 850