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

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

Neuron 1136 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.6410. Min Act: -0.0002

Data Index: 1063916 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.6536. Min Act: -0.0002

Data Index: 117058 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.6499. Min Act: -0.0003

Data Index: 320539 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.6511. Min Act: -0.0002

Data Index: 1348340 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.6048. Min Act: -0.0003

Data Index: 978857 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5907. Min Act: -0.0003

Data Index: 733550 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5894. Min Act: -0.0002

Data Index: 720655 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5692. Min Act: -0.0003

Data Index: 473804 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5639. Min Act: -0.0003

Data Index: 227916 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5556. Min Act: -0.0002

Data Index: 418406 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5509. Min Act: -0.0003

Data Index: 1099510 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5459. Min Act: -0.0002

Data Index: 49873 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5701. Min Act: -0.0002

Data Index: 671604 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5490. Min Act: -0.0002

Data Index: 1204631 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5474. Min Act: -0.0003

Data Index: 250963 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5449. Min Act: -0.0003

Data Index: 779625 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5428. Min Act: -0.0002

Data Index: 38265 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5219. Min Act: -0.0002

Data Index: 71801 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5347. Min Act: -0.0003

Data Index: 297449 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5334. Min Act: -0.0002

Data Index: 915214 (C4 (Web Text))

Max Activating Token Index: 858