Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3379 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0525. Min Act: -0.0002

Data Index: 607048 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0512. Min Act: -0.0002

Data Index: 305277 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0453. Min Act: -0.0002

Data Index: 952990 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0424. Min Act: -0.0002

Data Index: 96155 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1336519 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0386. Min Act: -0.0002

Data Index: 661266 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0382. Min Act: -0.0002

Data Index: 151736 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0377. Min Act: -0.0002

Data Index: 549243 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0376. Min Act: -0.0002

Data Index: 857334 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1250319 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0375. Min Act: -0.0002

Data Index: 351301 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0372. Min Act: -0.0002

Data Index: 960505 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0374. Min Act: -0.0002

Data Index: 237652 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0369. Min Act: -0.0002

Data Index: 232221 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0357. Min Act: -0.0002

Data Index: 185108 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1076074 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0364. Min Act: -0.0002

Data Index: 273871 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0359. Min Act: -0.0002

Data Index: 54074 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1113244 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0351. Min Act: -0.0002

Data Index: 794873 (C4 (Web Text))

Max Activating Token Index: 563