Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 119 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.2161. Min Act: -0.0001

Data Index: 907048 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.2061. Min Act: -0.0001

Data Index: 570447 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.2050. Min Act: -0.0001

Data Index: 69151 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1826. Min Act: -0.0001

Data Index: 334413 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1895. Min Act: -0.0001

Data Index: 1221416 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1966. Min Act: -0.0001

Data Index: 233074 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1841. Min Act: -0.0001

Data Index: 560890 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1813. Min Act: -0.0001

Data Index: 97304 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1024825 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1858. Min Act: -0.0001

Data Index: 819114 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1639. Min Act: -0.0001

Data Index: 814151 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1741. Min Act: -0.0001

Data Index: 997704 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1757. Min Act: -0.0001

Data Index: 471996 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1689. Min Act: -0.0001

Data Index: 1278825 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1687. Min Act: -0.0001

Data Index: 416869 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1675. Min Act: -0.0001

Data Index: 313096 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1598. Min Act: -0.0001

Data Index: 332792 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1595. Min Act: -0.0001

Data Index: 923473 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1570. Min Act: -0.0000

Data Index: 1346029 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1624. Min Act: 0.0001

Data Index: 1282406 (C4 (Web Text))

Max Activating Token Index: 350