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

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

Neuron 835 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0493. Min Act: -0.0005

Data Index: 788101 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0513. Min Act: -0.0005

Data Index: 125576 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0504. Min Act: -0.0006

Data Index: 593163 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0488. Min Act: -0.0006

Data Index: 901100 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0478. Min Act: -0.0006

Data Index: 343933 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0423. Min Act: -0.0006

Data Index: 819563 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0399. Min Act: -0.0005

Data Index: 874601 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0392. Min Act: -0.0006

Data Index: 873576 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0427. Min Act: -0.0005

Data Index: 725704 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0404. Min Act: -0.0005

Data Index: 413572 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0416. Min Act: -0.0006

Data Index: 782029 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0397. Min Act: -0.0005

Data Index: 419910 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0377. Min Act: -0.0006

Data Index: 705745 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0403. Min Act: -0.0006

Data Index: 430700 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0383. Min Act: -0.0006

Data Index: 324239 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0400. Min Act: -0.0006

Data Index: 584146 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0380. Min Act: -0.0005

Data Index: 907171 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0398. Min Act: -0.0005

Data Index: 916262 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0394. Min Act: -0.0006

Data Index: 1009047 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0360. Min Act: -0.0006

Data Index: 955200 (C4 (Web Text))

Max Activating Token Index: 923