Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3212 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1076. Min Act: -0.0001

Data Index: 1024889 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0952. Min Act: -0.0001

Data Index: 133630 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0855. Min Act: -0.0001

Data Index: 990629 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0781. Min Act: -0.0001

Data Index: 603406 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0681. Min Act: -0.0001

Data Index: 106980 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0801. Min Act: -0.0001

Data Index: 621931 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0778. Min Act: -0.0001

Data Index: 337569 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0719. Min Act: -0.0001

Data Index: 441656 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0722. Min Act: -0.0001

Data Index: 603323 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0659. Min Act: -0.0001

Data Index: 792330 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0657. Min Act: -0.0001

Data Index: 678937 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0602. Min Act: -0.0001

Data Index: 786273 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0735. Min Act: -0.0001

Data Index: 973440 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0677. Min Act: -0.0001

Data Index: 877403 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0651. Min Act: -0.0001

Data Index: 966132 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0653. Min Act: -0.0001

Data Index: 252386 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0716. Min Act: -0.0001

Data Index: 559534 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1107367 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0698. Min Act: -0.0001

Data Index: 548722 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0609. Min Act: -0.0001

Data Index: 1099965 (C4 (Web Text))

Max Activating Token Index: 1010