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

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

Neuron 2267 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1080. Min Act: -0.0002

Data Index: 288280 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1048. Min Act: -0.0002

Data Index: 1274340 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0991. Min Act: -0.0002

Data Index: 575454 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1049. Min Act: -0.0002

Data Index: 1269760 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0933. Min Act: -0.0002

Data Index: 738552 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0904. Min Act: -0.0002

Data Index: 339579 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0864. Min Act: -0.0002

Data Index: 1280264 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0943. Min Act: -0.0002

Data Index: 359829 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0913. Min Act: -0.0002

Data Index: 892351 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0739. Min Act: -0.0002

Data Index: 265193 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0821. Min Act: -0.0002

Data Index: 341995 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0761. Min Act: -0.0002

Data Index: 555593 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1342577 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0822. Min Act: -0.0002

Data Index: 791630 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0851. Min Act: -0.0002

Data Index: 577454 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1382885 (Python Code)

Max Activating Token Index: 455

Text #16

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0842. Min Act: -0.0002

Data Index: 428306 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0936. Min Act: -0.0002

Data Index: 969128 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0727. Min Act: -0.0002

Data Index: 1256633 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0802. Min Act: -0.0002

Data Index: 72323 (C4 (Web Text))

Max Activating Token Index: 249