Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1020 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1096229 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2602. Min Act: -0.0000

Data Index: 943533 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2626. Min Act: -0.0000

Data Index: 162534 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1270777 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2582. Min Act: -0.0000

Data Index: 108495 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2555. Min Act: -0.0000

Data Index: 683818 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2532. Min Act: -0.0000

Data Index: 941285 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2230. Min Act: -0.0000

Data Index: 803877 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2499. Min Act: -0.0000

Data Index: 233614 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1573551 (Python Code)

Max Activating Token Index: 952

Text #10

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2207. Min Act: -0.0000

Data Index: 714662 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2304. Min Act: -0.0000

Data Index: 455028 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2309. Min Act: -0.0000

Data Index: 81665 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1008132 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1324581 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2278. Min Act: -0.0000

Data Index: 992797 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2603. Min Act: -0.0000

Data Index: 742214 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2118. Min Act: -0.0000

Data Index: 1265028 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2258. Min Act: -0.0000

Data Index: 46763 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2155. Min Act: -0.0000

Data Index: 498175 (C4 (Web Text))

Max Activating Token Index: 984