Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 624 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0556. Min Act: -0.0003

Data Index: 1075609 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0486. Min Act: -0.0003

Data Index: 1193272 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0396. Min Act: -0.0003

Data Index: 112234 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0386. Min Act: -0.0003

Data Index: 429849 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0400. Min Act: -0.0003

Data Index: 505529 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0383. Min Act: -0.0003

Data Index: 739569 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0363. Min Act: -0.0003

Data Index: 608122 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0373. Min Act: -0.0004

Data Index: 537267 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0367. Min Act: -0.0003

Data Index: 167804 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0364. Min Act: -0.0003

Data Index: 1232359 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0361. Min Act: -0.0004

Data Index: 1274036 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1024279 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0349. Min Act: -0.0003

Data Index: 145543 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0346. Min Act: -0.0003

Data Index: 690456 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0345. Min Act: -0.0003

Data Index: 1147649 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0340. Min Act: -0.0004

Data Index: 155363 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0339. Min Act: -0.0003

Data Index: 694225 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0336. Min Act: -0.0003

Data Index: 1273769 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0332. Min Act: -0.0003

Data Index: 607504 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0325. Min Act: -0.0003

Data Index: 969314 (C4 (Web Text))

Max Activating Token Index: 121