Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1431 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0845. Min Act: -0.0002

Data Index: 1346287 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0773. Min Act: -0.0002

Data Index: 511687 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0814. Min Act: -0.0002

Data Index: 685574 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0796. Min Act: -0.0002

Data Index: 877328 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0802. Min Act: -0.0002

Data Index: 571496 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0751. Min Act: -0.0002

Data Index: 845120 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0735. Min Act: -0.0001

Data Index: 415217 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0705. Min Act: -0.0002

Data Index: 698130 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0743. Min Act: -0.0002

Data Index: 27086 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0706. Min Act: -0.0002

Data Index: 1262121 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0725. Min Act: -0.0002

Data Index: 51630 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0699. Min Act: -0.0002

Data Index: 123674 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0717. Min Act: -0.0002

Data Index: 626703 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0688. Min Act: -0.0001

Data Index: 48115 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0680. Min Act: -0.0002

Data Index: 984 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0692. Min Act: -0.0001

Data Index: 193325 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0664. Min Act: -0.0002

Data Index: 792298 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1098654 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0652. Min Act: -0.0002

Data Index: 503062 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0658. Min Act: -0.0001

Data Index: 656669 (C4 (Web Text))

Max Activating Token Index: 531