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

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

Neuron 1855 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: 1.0172. Min Range: -1.0172

Max Act: 1.0172. Min Act: -0.0002

Data Index: 128321 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 1.0172. Min Range: -1.0172

Max Act: 1.0104. Min Act: -0.0002

Data Index: 1136334 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 1.0172. Min Range: -1.0172

Max Act: 0.9133. Min Act: -0.0002

Data Index: 796000 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 1.0172. Min Range: -1.0172

Max Act: 0.8771. Min Act: -0.0002

Data Index: 474437 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 1.0172. Min Range: -1.0172

Max Act: 0.9366. Min Act: -0.0002

Data Index: 217789 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 1.0172. Min Range: -1.0172

Max Act: 0.8972. Min Act: -0.0002

Data Index: 229846 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 1.0172. Min Range: -1.0172

Max Act: 0.8659. Min Act: -0.0002

Data Index: 614459 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 1.0172. Min Range: -1.0172

Max Act: 0.8275. Min Act: -0.0002

Data Index: 183040 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 1.0172. Min Range: -1.0172

Max Act: 0.8405. Min Act: -0.0002

Data Index: 686376 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 1.0172. Min Range: -1.0172

Max Act: 0.7686. Min Act: -0.0002

Data Index: 723223 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 1.0172. Min Range: -1.0172

Max Act: 0.8099. Min Act: -0.0002

Data Index: 313332 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 1.0172. Min Range: -1.0172

Max Act: 0.8644. Min Act: -0.0002

Data Index: 1168471 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 1.0172. Min Range: -1.0172

Max Act: 0.8106. Min Act: -0.0002

Data Index: 884564 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 1.0172. Min Range: -1.0172

Max Act: 0.8268. Min Act: -0.0002

Data Index: 535555 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 1.0172. Min Range: -1.0172

Max Act: 0.8305. Min Act: -0.0002

Data Index: 1091947 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 1.0172. Min Range: -1.0172

Max Act: 0.8625. Min Act: -0.0002

Data Index: 1323596 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 1.0172. Min Range: -1.0172

Max Act: 0.7511. Min Act: -0.0002

Data Index: 839679 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 1.0172. Min Range: -1.0172

Max Act: 0.8353. Min Act: -0.0002

Data Index: 470576 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 1.0172. Min Range: -1.0172

Max Act: 0.8131. Min Act: -0.0002

Data Index: 222754 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 1.0172. Min Range: -1.0172

Max Act: 0.8029. Min Act: -0.0002

Data Index: 1282263 (C4 (Web Text))

Max Activating Token Index: 710