Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1900 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0447. Min Act: -0.0001

Data Index: 93281 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0474. Min Act: -0.0001

Data Index: 862940 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1111491 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0455. Min Act: -0.0001

Data Index: 650933 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0404. Min Act: -0.0001

Data Index: 175640 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0445. Min Act: -0.0001

Data Index: 315767 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0407. Min Act: -0.0001

Data Index: 77512 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0386. Min Act: -0.0001

Data Index: 697607 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0411. Min Act: -0.0001

Data Index: 1041059 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0386. Min Act: -0.0001

Data Index: 1309851 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0393. Min Act: -0.0001

Data Index: 338502 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0386. Min Act: -0.0001

Data Index: 510203 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0403. Min Act: -0.0001

Data Index: 563394 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0399. Min Act: -0.0001

Data Index: 48257 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0364. Min Act: -0.0001

Data Index: 1016340 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0375. Min Act: -0.0001

Data Index: 214977 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0369. Min Act: -0.0001

Data Index: 635910 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0398. Min Act: -0.0001

Data Index: 478093 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0369. Min Act: -0.0001

Data Index: 595557 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0360. Min Act: -0.0001

Data Index: 138493 (C4 (Web Text))

Max Activating Token Index: 198