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

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

Neuron 1332 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: 0.0505. Min Range: -0.0505

Max Act: 0.0505. Min Act: -0.0006

Data Index: 219930 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0423. Min Act: -0.0006

Data Index: 245826 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0400. Min Act: -0.0006

Data Index: 75877 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0415. Min Act: -0.0006

Data Index: 875199 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0366. Min Act: -0.0006

Data Index: 334948 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0380. Min Act: -0.0006

Data Index: 1124828 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0372. Min Act: -0.0006

Data Index: 76566 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0358. Min Act: -0.0006

Data Index: 821027 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0384. Min Act: -0.0006

Data Index: 1358205 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0375. Min Act: -0.0006

Data Index: 571261 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0366. Min Act: -0.0006

Data Index: 890327 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0394. Min Act: -0.0006

Data Index: 1036877 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0355. Min Act: -0.0006

Data Index: 576369 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0376. Min Act: -0.0006

Data Index: 776303 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0357. Min Act: -0.0006

Data Index: 141443 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0334. Min Act: -0.0006

Data Index: 465954 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0371. Min Act: -0.0005

Data Index: 295113 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0328. Min Act: -0.0006

Data Index: 610160 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0351. Min Act: -0.0006

Data Index: 517031 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0342. Min Act: -0.0006

Data Index: 652973 (C4 (Web Text))

Max Activating Token Index: 254