Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4895 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5703. Min Range: -1.5703

Max Act: 1.5703. Min Act: -0.0000

Data Index: 610083 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 1.5703. Min Range: -1.5703

Max Act: 1.3783. Min Act: -0.0000

Data Index: 127078 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 1.5703. Min Range: -1.5703

Max Act: 1.0961. Min Act: -0.0000

Data Index: 805504 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 1.5703. Min Range: -1.5703

Max Act: 1.0743. Min Act: -0.0000

Data Index: 975349 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 1.5703. Min Range: -1.5703

Max Act: 1.1269. Min Act: -0.0000

Data Index: 1185597 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 1.5703. Min Range: -1.5703

Max Act: 1.0607. Min Act: -0.0000

Data Index: 520385 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 1.5703. Min Range: -1.5703

Max Act: 0.9560. Min Act: -0.0000

Data Index: 1355294 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 1.5703. Min Range: -1.5703

Max Act: 1.0153. Min Act: -0.0000

Data Index: 354312 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 1.5703. Min Range: -1.5703

Max Act: 0.9908. Min Act: -0.0000

Data Index: 469482 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 1.5703. Min Range: -1.5703

Max Act: 0.9075. Min Act: -0.0000

Data Index: 976348 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 1.5703. Min Range: -1.5703

Max Act: 0.7781. Min Act: -0.0000

Data Index: 929791 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 1.5703. Min Range: -1.5703

Max Act: 0.8975. Min Act: -0.0000

Data Index: 11064 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 1.5703. Min Range: -1.5703

Max Act: 0.8685. Min Act: -0.0000

Data Index: 280329 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 1.5703. Min Range: -1.5703

Max Act: 0.8662. Min Act: -0.0000

Data Index: 908464 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 1.5703. Min Range: -1.5703

Max Act: 0.8630. Min Act: -0.0000

Data Index: 985940 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 1.5703. Min Range: -1.5703

Max Act: 0.8634. Min Act: -0.0000

Data Index: 272035 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 1.5703. Min Range: -1.5703

Max Act: 0.8641. Min Act: -0.0000

Data Index: 109101 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 1.5703. Min Range: -1.5703

Max Act: 0.8170. Min Act: -0.0000

Data Index: 441646 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 1.5703. Min Range: -1.5703

Max Act: 0.7624. Min Act: -0.0000

Data Index: 739881 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 1.5703. Min Range: -1.5703

Max Act: 0.8060. Min Act: -0.0000

Data Index: 165429 (C4 (Web Text))

Max Activating Token Index: 785