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

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

Neuron 2310 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0765. Min Act: -0.0000

Data Index: 569091 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0809. Min Act: -0.0000

Data Index: 533355 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0772. Min Act: -0.0000

Data Index: 1196537 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0695. Min Act: -0.0000

Data Index: 84222 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0639. Min Act: -0.0000

Data Index: 727244 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0582. Min Act: -0.0000

Data Index: 683101 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1608501 (Python Code)

Max Activating Token Index: 226

Text #7

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0593. Min Act: -0.0000

Data Index: 453206 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0563. Min Act: -0.0000

Data Index: 78343 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0522. Min Act: -0.0000

Data Index: 1217499 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1403642 (Python Code)

Max Activating Token Index: 318

Text #11

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0506. Min Act: -0.0000

Data Index: 1601580 (Python Code)

Max Activating Token Index: 219

Text #12

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0531. Min Act: -0.0000

Data Index: 1009507 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0493. Min Act: -0.0000

Data Index: 1388385 (Python Code)

Max Activating Token Index: 60

Text #14

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0489. Min Act: -0.0000

Data Index: 660432 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0460. Min Act: -0.0000

Data Index: 196853 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0472. Min Act: -0.0000

Data Index: 1593198 (Python Code)

Max Activating Token Index: 918

Text #17

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0498. Min Act: -0.0000

Data Index: 1475548 (Python Code)

Max Activating Token Index: 1005

Text #18

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0456. Min Act: -0.0000

Data Index: 1599310 (Python Code)

Max Activating Token Index: 761

Text #19

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0455. Min Act: -0.0000

Data Index: 844186 (C4 (Web Text))

Max Activating Token Index: 144