Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3991 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1380. Min Range: -1.1380

Max Act: 1.1380. Min Act: -0.0001

Data Index: 417867 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 1.1380. Min Range: -1.1380

Max Act: 1.0300. Min Act: -0.0001

Data Index: 811983 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 1.1380. Min Range: -1.1380

Max Act: 1.0233. Min Act: -0.0001

Data Index: 121754 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 1.1380. Min Range: -1.1380

Max Act: 0.9382. Min Act: -0.0001

Data Index: 575240 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 1.1380. Min Range: -1.1380

Max Act: 0.9953. Min Act: -0.0001

Data Index: 194421 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 1.1380. Min Range: -1.1380

Max Act: 0.9839. Min Act: -0.0001

Data Index: 1048011 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 1.1380. Min Range: -1.1380

Max Act: 0.9423. Min Act: -0.0001

Data Index: 1263556 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 1.1380. Min Range: -1.1380

Max Act: 0.9460. Min Act: -0.0001

Data Index: 1091517 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 1.1380. Min Range: -1.1380

Max Act: 0.8485. Min Act: -0.0001

Data Index: 301459 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 1.1380. Min Range: -1.1380

Max Act: 1.0116. Min Act: -0.0001

Data Index: 1413527 (Python Code)

Max Activating Token Index: 748

Text #10

Max Range: 1.1380. Min Range: -1.1380

Max Act: 0.9702. Min Act: -0.0001

Data Index: 1261472 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 1.1380. Min Range: -1.1380

Max Act: 0.9534. Min Act: -0.0001

Data Index: 655170 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 1.1380. Min Range: -1.1380

Max Act: 0.9534. Min Act: -0.0001

Data Index: 799710 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 1.1380. Min Range: -1.1380

Max Act: 0.9358. Min Act: -0.0001

Data Index: 526166 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 1.1380. Min Range: -1.1380

Max Act: 0.8953. Min Act: -0.0001

Data Index: 999240 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 1.1380. Min Range: -1.1380

Max Act: 0.9642. Min Act: -0.0001

Data Index: 1574902 (Python Code)

Max Activating Token Index: 767

Text #16

Max Range: 1.1380. Min Range: -1.1380

Max Act: 0.8644. Min Act: -0.0001

Data Index: 1350871 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 1.1380. Min Range: -1.1380

Max Act: 0.8389. Min Act: -0.0001

Data Index: 532126 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 1.1380. Min Range: -1.1380

Max Act: 0.9415. Min Act: -0.0001

Data Index: 137880 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 1.1380. Min Range: -1.1380

Max Act: 0.8788. Min Act: -0.0001

Data Index: 1304834 (C4 (Web Text))

Max Activating Token Index: 548