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

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

Neuron 2789 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1832. Min Range: -1.1832

Max Act: 1.1832. Min Act: -0.0000

Data Index: 1047373 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 1.1832. Min Range: -1.1832

Max Act: 0.9731. Min Act: -0.0000

Data Index: 330068 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 1.1832. Min Range: -1.1832

Max Act: 0.8775. Min Act: -0.0000

Data Index: 704681 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 1.1832. Min Range: -1.1832

Max Act: 0.9062. Min Act: -0.0000

Data Index: 478344 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 1.1832. Min Range: -1.1832

Max Act: 0.8388. Min Act: -0.0000

Data Index: 1266680 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 1.1832. Min Range: -1.1832

Max Act: 0.8116. Min Act: -0.0000

Data Index: 774708 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 1.1832. Min Range: -1.1832

Max Act: 0.8636. Min Act: -0.0000

Data Index: 31914 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 1.1832. Min Range: -1.1832

Max Act: 0.7856. Min Act: -0.0000

Data Index: 838243 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 1.1832. Min Range: -1.1832

Max Act: 0.8783. Min Act: -0.0000

Data Index: 1287814 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 1.1832. Min Range: -1.1832

Max Act: 0.8707. Min Act: -0.0000

Data Index: 592324 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 1.1832. Min Range: -1.1832

Max Act: 0.9234. Min Act: -0.0000

Data Index: 484830 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 1.1832. Min Range: -1.1832

Max Act: 0.8431. Min Act: -0.0000

Data Index: 452341 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 1.1832. Min Range: -1.1832

Max Act: 0.7887. Min Act: -0.0000

Data Index: 596212 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 1.1832. Min Range: -1.1832

Max Act: 0.8845. Min Act: -0.0000

Data Index: 1002451 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 1.1832. Min Range: -1.1832

Max Act: 0.7149. Min Act: -0.0000

Data Index: 1318381 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 1.1832. Min Range: -1.1832

Max Act: 0.7483. Min Act: -0.0000

Data Index: 99845 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 1.1832. Min Range: -1.1832

Max Act: 0.8027. Min Act: -0.0000

Data Index: 380625 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 1.1832. Min Range: -1.1832

Max Act: 0.7407. Min Act: -0.0000

Data Index: 559743 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 1.1832. Min Range: -1.1832

Max Act: 0.7111. Min Act: -0.0000

Data Index: 1058741 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 1.1832. Min Range: -1.1832

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1269274 (C4 (Web Text))

Max Activating Token Index: 655