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

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

Neuron 1048 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.9697. Min Act: -0.0000

Data Index: 804029 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.9035. Min Act: -0.0000

Data Index: 20254 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8589. Min Act: -0.0000

Data Index: 823708 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8740. Min Act: -0.0000

Data Index: 425912 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7862. Min Act: -0.0000

Data Index: 483923 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7677. Min Act: -0.0000

Data Index: 691580 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7820. Min Act: -0.0000

Data Index: 761304 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7540. Min Act: -0.0000

Data Index: 1113407 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7127. Min Act: -0.0000

Data Index: 333615 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7021. Min Act: -0.0000

Data Index: 141101 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6918. Min Act: -0.0000

Data Index: 500900 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6599. Min Act: -0.0000

Data Index: 1040230 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6757. Min Act: -0.0000

Data Index: 499058 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6729. Min Act: -0.0000

Data Index: 553339 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6631. Min Act: -0.0000

Data Index: 198940 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6423. Min Act: -0.0000

Data Index: 628485 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6574. Min Act: -0.0000

Data Index: 316934 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6720. Min Act: -0.0000

Data Index: 724320 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6531. Min Act: -0.0000

Data Index: 222421 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1183356 (C4 (Web Text))

Max Activating Token Index: 1019