Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 335 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0545. Min Act: -0.0003

Data Index: 836261 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0521. Min Act: -0.0003

Data Index: 60865 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0558. Min Act: -0.0003

Data Index: 886497 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0527. Min Act: -0.0003

Data Index: 878129 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0526. Min Act: -0.0003

Data Index: 33475 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0508. Min Act: -0.0003

Data Index: 407434 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0507. Min Act: -0.0003

Data Index: 488173 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0495. Min Act: -0.0003

Data Index: 721047 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0483. Min Act: -0.0003

Data Index: 462752 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1206354 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1114732 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0478. Min Act: -0.0004

Data Index: 887822 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0465. Min Act: -0.0003

Data Index: 545868 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0475. Min Act: -0.0004

Data Index: 45526 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0464. Min Act: -0.0003

Data Index: 311672 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0467. Min Act: -0.0003

Data Index: 379981 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0478. Min Act: -0.0004

Data Index: 384415 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0472. Min Act: -0.0003

Data Index: 292538 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0456. Min Act: -0.0003

Data Index: 726110 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1019293 (C4 (Web Text))

Max Activating Token Index: 579