Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1072 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0718. Min Act: -0.0006

Data Index: 209898 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0645. Min Act: -0.0006

Data Index: 128579 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0631. Min Act: -0.0006

Data Index: 254888 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0613. Min Act: -0.0006

Data Index: 218533 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0599. Min Act: -0.0006

Data Index: 1086219 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0574. Min Act: -0.0006

Data Index: 578273 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0585. Min Act: -0.0006

Data Index: 53182 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0595. Min Act: -0.0006

Data Index: 1145372 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0577. Min Act: -0.0006

Data Index: 886847 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0588. Min Act: -0.0006

Data Index: 864091 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0599. Min Act: -0.0006

Data Index: 438562 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0567. Min Act: -0.0006

Data Index: 542756 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0540. Min Act: -0.0006

Data Index: 299295 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0552. Min Act: -0.0006

Data Index: 865228 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0559. Min Act: -0.0006

Data Index: 981182 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0545. Min Act: -0.0006

Data Index: 242496 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0540. Min Act: -0.0006

Data Index: 437739 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0549. Min Act: -0.0006

Data Index: 100612 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0536. Min Act: -0.0006

Data Index: 1269976 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0545. Min Act: -0.0006

Data Index: 1019236 (C4 (Web Text))

Max Activating Token Index: 483