Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1510 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0607. Min Act: -0.0002

Data Index: 918243 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0689. Min Act: -0.0002

Data Index: 295942 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0639. Min Act: -0.0002

Data Index: 33491 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0578. Min Act: -0.0002

Data Index: 972311 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0586. Min Act: -0.0002

Data Index: 264568 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0587. Min Act: -0.0002

Data Index: 250114 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1020726 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0598. Min Act: -0.0002

Data Index: 223441 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0569. Min Act: -0.0002

Data Index: 3556 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0533. Min Act: -0.0002

Data Index: 950728 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0568. Min Act: -0.0002

Data Index: 175963 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0521. Min Act: -0.0002

Data Index: 292495 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0560. Min Act: -0.0002

Data Index: 547560 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1299243 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0546. Min Act: -0.0002

Data Index: 180848 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1260355 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0538. Min Act: -0.0002

Data Index: 665224 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0538. Min Act: -0.0002

Data Index: 193508 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0542. Min Act: -0.0002

Data Index: 383810 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0504. Min Act: -0.0002

Data Index: 49206 (C4 (Web Text))

Max Activating Token Index: 337