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

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

Neuron 2805 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: 0.0797. Min Range: -0.0797

Max Act: 0.0760. Min Act: -0.0001

Data Index: 1338209 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0797. Min Act: -0.0002

Data Index: 599617 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0749. Min Act: -0.0001

Data Index: 429837 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0752. Min Act: -0.0001

Data Index: 359432 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0690. Min Act: -0.0001

Data Index: 313064 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0672. Min Act: -0.0001

Data Index: 419477 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0671. Min Act: -0.0001

Data Index: 822391 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0688. Min Act: -0.0001

Data Index: 1206673 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0687. Min Act: -0.0001

Data Index: 166768 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0581. Min Act: -0.0001

Data Index: 628099 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0632. Min Act: -0.0002

Data Index: 338422 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1185575 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0550. Min Act: -0.0001

Data Index: 44673 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0637. Min Act: -0.0001

Data Index: 1121810 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0636. Min Act: -0.0001

Data Index: 67986 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0560. Min Act: -0.0001

Data Index: 627078 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0603. Min Act: -0.0001

Data Index: 553182 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0540. Min Act: -0.0001

Data Index: 256937 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0598. Min Act: -0.0001

Data Index: 586815 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0489. Min Act: -0.0001

Data Index: 208352 (C4 (Web Text))

Max Activating Token Index: 816