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

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

Neuron 656 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.9761. Min Act: -0.0000

Data Index: 168075 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.9601. Min Act: -0.0000

Data Index: 684596 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.7126. Min Act: -0.0000

Data Index: 192017 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.7278. Min Act: -0.0000

Data Index: 53112 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.7214. Min Act: -0.0000

Data Index: 850184 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1074322 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1314693 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.6023. Min Act: -0.0000

Data Index: 1117997 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.5748. Min Act: -0.0000

Data Index: 123297 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1163541 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.6392. Min Act: -0.0000

Data Index: 433304 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.5904. Min Act: -0.0000

Data Index: 547845 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.4405. Min Act: -0.0000

Data Index: 641091 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.5769. Min Act: -0.0000

Data Index: 618660 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.5941. Min Act: -0.0000

Data Index: 662136 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.5398. Min Act: -0.0000

Data Index: 18484 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.5655. Min Act: -0.0000

Data Index: 460902 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1146687 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.5392. Min Act: -0.0000

Data Index: 497710 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.5513. Min Act: -0.0000

Data Index: 399204 (C4 (Web Text))

Max Activating Token Index: 857