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

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

Neuron 72 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.6455. Min Act: -0.0000

Data Index: 907119 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.8437. Min Act: -0.0000

Data Index: 1021316 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.6599. Min Act: -0.0000

Data Index: 1079075 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.8137. Min Act: -0.0000

Data Index: 1251875 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.4735. Min Act: -0.0000

Data Index: 84900 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.6645. Min Act: -0.0000

Data Index: 1156953 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.4811. Min Act: -0.0000

Data Index: 804803 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.5764. Min Act: -0.0000

Data Index: 591375 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.6730. Min Act: -0.0000

Data Index: 382967 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.5401. Min Act: -0.0000

Data Index: 267363 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.3860. Min Act: -0.0000

Data Index: 618052 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.5434. Min Act: -0.0000

Data Index: 683447 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.4958. Min Act: -0.0000

Data Index: 1237747 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.6734. Min Act: -0.0000

Data Index: 94194 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.6515. Min Act: -0.0000

Data Index: 184593 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.4697. Min Act: -0.0000

Data Index: 737621 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.4697. Min Act: -0.0000

Data Index: 383113 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.4750. Min Act: -0.0000

Data Index: 411597 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.3287. Min Act: -0.0000

Data Index: 751808 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 3.8437. Min Range: -3.8437

Max Act: 3.4608. Min Act: -0.0000

Data Index: 458781 (C4 (Web Text))

Max Activating Token Index: 628