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

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

Neuron 2256 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.6817. Min Act: -0.0002

Data Index: 701380 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.6551. Min Act: -0.0002

Data Index: 631541 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5922. Min Act: -0.0002

Data Index: 311794 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5840. Min Act: -0.0002

Data Index: 55744 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5435. Min Act: -0.0002

Data Index: 978468 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5557. Min Act: -0.0002

Data Index: 1288310 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.6107. Min Act: -0.0002

Data Index: 314667 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5502. Min Act: -0.0002

Data Index: 359927 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5631. Min Act: -0.0002

Data Index: 336379 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5649. Min Act: -0.0002

Data Index: 1171565 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5808. Min Act: -0.0002

Data Index: 521213 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5445. Min Act: -0.0002

Data Index: 268377 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5635. Min Act: -0.0002

Data Index: 632359 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5565. Min Act: -0.0002

Data Index: 1263553 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5499. Min Act: -0.0002

Data Index: 302448 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5908. Min Act: -0.0002

Data Index: 1056633 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5640. Min Act: -0.0002

Data Index: 107907 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5691. Min Act: -0.0002

Data Index: 494532 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5474. Min Act: -0.0002

Data Index: 112759 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.6817. Min Range: -0.6817

Max Act: 0.5612. Min Act: -0.0002

Data Index: 1286000 (C4 (Web Text))

Max Activating Token Index: 301