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

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

Neuron 704 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0431. Min Act: -0.0004

Data Index: 742854 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0477. Min Act: -0.0004

Data Index: 1603879 (Python Code)

Max Activating Token Index: 509

Text #2

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0326. Min Act: -0.0004

Data Index: 518206 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0337. Min Act: -0.0004

Data Index: 1009974 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0412. Min Act: -0.0004

Data Index: 1258445 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0411. Min Act: -0.0004

Data Index: 98330 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0409. Min Act: -0.0004

Data Index: 1276572 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0369. Min Act: -0.0004

Data Index: 1294902 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0422. Min Act: -0.0004

Data Index: 1142385 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0403. Min Act: -0.0004

Data Index: 668369 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0395. Min Act: -0.0004

Data Index: 811590 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0412. Min Act: -0.0004

Data Index: 515473 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0372. Min Act: -0.0004

Data Index: 508740 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0318. Min Act: -0.0004

Data Index: 155412 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0393. Min Act: -0.0004

Data Index: 379062 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0349. Min Act: -0.0004

Data Index: 289525 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0332. Min Act: -0.0004

Data Index: 206767 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0360. Min Act: -0.0004

Data Index: 759228 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0384. Min Act: -0.0004

Data Index: 535323 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0345. Min Act: -0.0004

Data Index: 1258808 (C4 (Web Text))

Max Activating Token Index: 342