Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 298 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1090250 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0525. Min Act: -0.0000

Data Index: 1120012 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0461. Min Act: -0.0000

Data Index: 487243 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0395. Min Act: -0.0000

Data Index: 1298257 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0381. Min Act: -0.0000

Data Index: 977082 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0428. Min Act: -0.0000

Data Index: 304974 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0423. Min Act: -0.0000

Data Index: 917366 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0472. Min Act: -0.0000

Data Index: 51220 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0440. Min Act: -0.0000

Data Index: 358782 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0394. Min Act: -0.0000

Data Index: 362244 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0385. Min Act: -0.0000

Data Index: 291851 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0373. Min Act: -0.0000

Data Index: 707302 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0389. Min Act: -0.0000

Data Index: 526060 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0400. Min Act: -0.0000

Data Index: 596492 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0402. Min Act: -0.0000

Data Index: 334242 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0386. Min Act: -0.0000

Data Index: 36134 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0370. Min Act: -0.0000

Data Index: 845143 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0369. Min Act: -0.0000

Data Index: 171497 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0401. Min Act: -0.0000

Data Index: 1552830 (Python Code)

Max Activating Token Index: 670

Text #19

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0352. Min Act: -0.0000

Data Index: 1323837 (C4 (Web Text))

Max Activating Token Index: 1010