Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3697 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0915. Min Act: -0.0002

Data Index: 530641 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0920. Min Act: -0.0002

Data Index: 113118 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0861. Min Act: -0.0002

Data Index: 708578 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0942. Min Act: -0.0001

Data Index: 353674 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0817. Min Act: -0.0002

Data Index: 112364 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0860. Min Act: -0.0002

Data Index: 12547 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1002976 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0839. Min Act: -0.0002

Data Index: 64550 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0682. Min Act: -0.0001

Data Index: 1165528 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0874. Min Act: -0.0002

Data Index: 815253 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0824. Min Act: -0.0002

Data Index: 445185 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0783. Min Act: -0.0001

Data Index: 776177 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1251401 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0826. Min Act: -0.0002

Data Index: 336335 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0839. Min Act: -0.0002

Data Index: 859480 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0832. Min Act: -0.0001

Data Index: 1028740 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1112787 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1141842 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0743. Min Act: -0.0001

Data Index: 1095117 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0740. Min Act: -0.0001

Data Index: 337533 (C4 (Web Text))

Max Activating Token Index: 523