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

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

Neuron 254 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0087. Min Range: -7.0087

Max Act: 7.0087. Min Act: -0.0000

Data Index: 1582940 (Python Code)

Max Activating Token Index: 688

Text #1

Max Range: 7.0087. Min Range: -7.0087

Max Act: 6.5522. Min Act: -0.0000

Data Index: 1395979 (Python Code)

Max Activating Token Index: 226

Text #2

Max Range: 7.0087. Min Range: -7.0087

Max Act: 6.4560. Min Act: -0.0000

Data Index: 1478903 (Python Code)

Max Activating Token Index: 382

Text #3

Max Range: 7.0087. Min Range: -7.0087

Max Act: 6.3565. Min Act: -0.0000

Data Index: 1513720 (Python Code)

Max Activating Token Index: 510

Text #4

Max Range: 7.0087. Min Range: -7.0087

Max Act: 5.7968. Min Act: -0.0000

Data Index: 1577466 (Python Code)

Max Activating Token Index: 308

Text #5

Max Range: 7.0087. Min Range: -7.0087

Max Act: 5.9193. Min Act: -0.0000

Data Index: 1491147 (Python Code)

Max Activating Token Index: 210

Text #6

Max Range: 7.0087. Min Range: -7.0087

Max Act: 5.3744. Min Act: -0.0000

Data Index: 1601625 (Python Code)

Max Activating Token Index: 208

Text #7

Max Range: 7.0087. Min Range: -7.0087

Max Act: 6.0001. Min Act: -0.0000

Data Index: 1490187 (Python Code)

Max Activating Token Index: 225

Text #8

Max Range: 7.0087. Min Range: -7.0087

Max Act: 5.5800. Min Act: -0.0000

Data Index: 1466882 (Python Code)

Max Activating Token Index: 399

Text #9

Max Range: 7.0087. Min Range: -7.0087

Max Act: 5.5499. Min Act: -0.0000

Data Index: 1558554 (Python Code)

Max Activating Token Index: 588

Text #10

Max Range: 7.0087. Min Range: -7.0087

Max Act: 5.8403. Min Act: -0.0000

Data Index: 1445204 (Python Code)

Max Activating Token Index: 542

Text #11

Max Range: 7.0087. Min Range: -7.0087

Max Act: 5.6377. Min Act: -0.0000

Data Index: 1644924 (Python Code)

Max Activating Token Index: 931

Text #12

Max Range: 7.0087. Min Range: -7.0087

Max Act: 5.4159. Min Act: -0.0000

Data Index: 1517432 (Python Code)

Max Activating Token Index: 506

Text #13

Max Range: 7.0087. Min Range: -7.0087

Max Act: 5.5927. Min Act: -0.0000

Data Index: 1452984 (Python Code)

Max Activating Token Index: 305

Text #14

Max Range: 7.0087. Min Range: -7.0087

Max Act: 5.0975. Min Act: -0.0000

Data Index: 1526228 (Python Code)

Max Activating Token Index: 408

Text #15

Max Range: 7.0087. Min Range: -7.0087

Max Act: 5.4091. Min Act: -0.0000

Data Index: 1601904 (Python Code)

Max Activating Token Index: 415

Text #16

Max Range: 7.0087. Min Range: -7.0087

Max Act: 5.2252. Min Act: -0.0000

Data Index: 1579607 (Python Code)

Max Activating Token Index: 553

Text #17

Max Range: 7.0087. Min Range: -7.0087

Max Act: 5.3353. Min Act: -0.0000

Data Index: 1603922 (Python Code)

Max Activating Token Index: 648

Text #18

Max Range: 7.0087. Min Range: -7.0087

Max Act: 4.6671. Min Act: -0.0000

Data Index: 1502830 (Python Code)

Max Activating Token Index: 862

Text #19

Max Range: 7.0087. Min Range: -7.0087

Max Act: 4.8435. Min Act: -0.0000

Data Index: 1541267 (Python Code)

Max Activating Token Index: 89