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

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

Neuron 3353 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3612. Min Range: -7.3612

Max Act: 7.3612. Min Act: -0.0000

Data Index: 1336699 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 7.3612. Min Range: -7.3612

Max Act: 7.2521. Min Act: -0.0000

Data Index: 129299 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 7.3612. Min Range: -7.3612

Max Act: 7.2350. Min Act: -0.0000

Data Index: 870883 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 7.3612. Min Range: -7.3612

Max Act: 7.2961. Min Act: -0.0000

Data Index: 76261 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 7.3612. Min Range: -7.3612

Max Act: 7.1377. Min Act: -0.0000

Data Index: 707162 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 7.3612. Min Range: -7.3612

Max Act: 7.2559. Min Act: -0.0000

Data Index: 1093086 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 7.3612. Min Range: -7.3612

Max Act: 7.1786. Min Act: -0.0000

Data Index: 882191 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 7.3612. Min Range: -7.3612

Max Act: 7.1343. Min Act: -0.0000

Data Index: 727678 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 7.3612. Min Range: -7.3612

Max Act: 7.0789. Min Act: -0.0000

Data Index: 745178 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 7.3612. Min Range: -7.3612

Max Act: 7.0889. Min Act: -0.0000

Data Index: 355726 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 7.3612. Min Range: -7.3612

Max Act: 7.0381. Min Act: -0.0000

Data Index: 1353642 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 7.3612. Min Range: -7.3612

Max Act: 7.0202. Min Act: -0.0000

Data Index: 680921 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 7.3612. Min Range: -7.3612

Max Act: 6.8267. Min Act: -0.0000

Data Index: 144345 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 7.3612. Min Range: -7.3612

Max Act: 6.9350. Min Act: -0.0000

Data Index: 1199838 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 7.3612. Min Range: -7.3612

Max Act: 6.9234. Min Act: -0.0000

Data Index: 342251 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 7.3612. Min Range: -7.3612

Max Act: 6.9237. Min Act: -0.0000

Data Index: 856554 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 7.3612. Min Range: -7.3612

Max Act: 6.8546. Min Act: -0.0000

Data Index: 611706 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 7.3612. Min Range: -7.3612

Max Act: 6.8623. Min Act: -0.0000

Data Index: 1069552 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 7.3612. Min Range: -7.3612

Max Act: 7.2231. Min Act: -0.0000

Data Index: 400976 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 7.3612. Min Range: -7.3612

Max Act: 6.6233. Min Act: -0.0000

Data Index: 1012698 (C4 (Web Text))

Max Activating Token Index: 980