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

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

Neuron 4610 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1546. Min Act: -0.0000

Data Index: 357047 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1489. Min Act: -0.0000

Data Index: 770280 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1486. Min Act: -0.0000

Data Index: 982748 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1382. Min Act: -0.0000

Data Index: 698483 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1359. Min Act: -0.0000

Data Index: 983363 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1106. Min Act: -0.0000

Data Index: 1591610 (Python Code)

Max Activating Token Index: 812

Text #6

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1176. Min Act: -0.0000

Data Index: 1205526 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1169. Min Act: -0.0000

Data Index: 1304495 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1053. Min Act: -0.0000

Data Index: 307210 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1014. Min Act: 0.0000

Data Index: 1613158 (Python Code)

Max Activating Token Index: 462

Text #10

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1204201 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0992. Min Act: -0.0000

Data Index: 1435386 (Python Code)

Max Activating Token Index: 581

Text #12

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1006. Min Act: -0.0000

Data Index: 1352029 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1023. Min Act: -0.0000

Data Index: 1571067 (Python Code)

Max Activating Token Index: 645

Text #14

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0995. Min Act: -0.0000

Data Index: 1419629 (Python Code)

Max Activating Token Index: 236

Text #15

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0930. Min Act: 0.0000

Data Index: 1607342 (Python Code)

Max Activating Token Index: 195

Text #16

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0967. Min Act: -0.0000

Data Index: 1409633 (Python Code)

Max Activating Token Index: 828

Text #17

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1087614 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0934. Min Act: 0.0000

Data Index: 1570472 (Python Code)

Max Activating Token Index: 666

Text #19

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0951. Min Act: 0.0000

Data Index: 1043239 (C4 (Web Text))

Max Activating Token Index: 819