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

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

Neuron 1913 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.6743. Min Act: -0.0000

Data Index: 1323482 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.6905. Min Act: -0.0000

Data Index: 927694 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.6332. Min Act: -0.0000

Data Index: 356248 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.5818. Min Act: -0.0000

Data Index: 533337 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.6157. Min Act: -0.0000

Data Index: 280115 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1010633 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1254150 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.6494. Min Act: -0.0000

Data Index: 233212 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.5822. Min Act: -0.0000

Data Index: 481 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1203248 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.5750. Min Act: -0.0000

Data Index: 17240 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1212635 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1133853 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.6189. Min Act: -0.0000

Data Index: 236542 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1075054 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.5426. Min Act: -0.0000

Data Index: 508046 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.5738. Min Act: -0.0000

Data Index: 952815 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.5790. Min Act: -0.0000

Data Index: 493835 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.5303. Min Act: -0.0000

Data Index: 1250114 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.6905. Min Range: -0.6905

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1079126 (C4 (Web Text))

Max Activating Token Index: 411