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

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

Neuron 318 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0441. Min Act: -0.0003

Data Index: 906494 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0399. Min Act: -0.0004

Data Index: 1317767 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0397. Min Act: -0.0003

Data Index: 981547 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0398. Min Act: -0.0003

Data Index: 13019 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1050918 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1091262 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1230597 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1318838 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0374. Min Act: -0.0003

Data Index: 892239 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0373. Min Act: -0.0003

Data Index: 182448 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0370. Min Act: -0.0003

Data Index: 1263109 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0364. Min Act: -0.0003

Data Index: 869633 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0359. Min Act: -0.0004

Data Index: 409904 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0370. Min Act: -0.0003

Data Index: 250556 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0351. Min Act: -0.0003

Data Index: 177816 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0358. Min Act: -0.0002

Data Index: 554817 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0356. Min Act: -0.0003

Data Index: 67239 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0357. Min Act: -0.0003

Data Index: 319458 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0350. Min Act: -0.0003

Data Index: 551121 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0358. Min Act: -0.0004

Data Index: 1224855 (C4 (Web Text))

Max Activating Token Index: 257