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

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

Neuron 2284 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1791. Min Act: -0.0001

Data Index: 360665 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1783. Min Act: -0.0001

Data Index: 264805 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1624. Min Act: -0.0001

Data Index: 1036787 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1671. Min Act: -0.0001

Data Index: 61720 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1572. Min Act: -0.0001

Data Index: 1205711 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1222318 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1595. Min Act: -0.0001

Data Index: 672791 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1532. Min Act: -0.0001

Data Index: 1101353 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1580. Min Act: -0.0000

Data Index: 67775 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1467. Min Act: -0.0001

Data Index: 1303759 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1522. Min Act: -0.0000

Data Index: 325544 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1468. Min Act: -0.0001

Data Index: 238298 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1191798 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1476. Min Act: -0.0001

Data Index: 1167822 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1523. Min Act: -0.0001

Data Index: 1032049 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1423. Min Act: -0.0001

Data Index: 1313482 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1460. Min Act: -0.0001

Data Index: 877824 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1436. Min Act: -0.0001

Data Index: 629459 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1418. Min Act: -0.0001

Data Index: 59554 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1424. Min Act: -0.0000

Data Index: 238962 (C4 (Web Text))

Max Activating Token Index: 520