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

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

Neuron 1384 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1165158 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 1.1456. Min Range: -1.1456

Max Act: 1.1456. Min Act: -0.0000

Data Index: 25762 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.9798. Min Act: -0.0000

Data Index: 421105 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.8756. Min Act: -0.0000

Data Index: 1269688 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1002597 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.8575. Min Act: -0.0000

Data Index: 729181 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.8865. Min Act: -0.0000

Data Index: 96572 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.7581. Min Act: -0.0000

Data Index: 954315 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.6868. Min Act: -0.0000

Data Index: 253405 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.7223. Min Act: -0.0000

Data Index: 364752 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.6724. Min Act: -0.0000

Data Index: 1369862 (Python Code)

Max Activating Token Index: 376

Text #11

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.7145. Min Act: -0.0000

Data Index: 594783 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1060313 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.6827. Min Act: -0.0000

Data Index: 897788 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.7099. Min Act: -0.0000

Data Index: 352402 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.6626. Min Act: -0.0000

Data Index: 390127 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.7062. Min Act: -0.0000

Data Index: 189399 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.7061. Min Act: -0.0000

Data Index: 188165 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.6540. Min Act: -0.0000

Data Index: 459728 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 1.1456. Min Range: -1.1456

Max Act: 0.6129. Min Act: -0.0000

Data Index: 9238 (C4 (Web Text))

Max Activating Token Index: 211