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

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

Neuron 492 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0455. Min Act: -0.0001

Data Index: 366561 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0471. Min Act: -0.0001

Data Index: 939135 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0395. Min Act: -0.0001

Data Index: 1048946 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0411. Min Act: -0.0001

Data Index: 148369 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0410. Min Act: -0.0001

Data Index: 511001 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0410. Min Act: -0.0001

Data Index: 594397 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0409. Min Act: -0.0001

Data Index: 931791 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0401. Min Act: -0.0001

Data Index: 245262 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0370. Min Act: -0.0001

Data Index: 549619 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0382. Min Act: -0.0001

Data Index: 212093 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0382. Min Act: -0.0001

Data Index: 555091 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0377. Min Act: -0.0001

Data Index: 972323 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0388. Min Act: -0.0001

Data Index: 618376 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0389. Min Act: -0.0001

Data Index: 127293 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1225943 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0349. Min Act: -0.0001

Data Index: 1141052 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1148824 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1089439 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0347. Min Act: -0.0001

Data Index: 389126 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0346. Min Act: -0.0001

Data Index: 680300 (C4 (Web Text))

Max Activating Token Index: 63