Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3336 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0482. Min Act: -0.0003

Data Index: 435534 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0412. Min Act: -0.0003

Data Index: 95201 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0417. Min Act: -0.0003

Data Index: 1379444 (Python Code)

Max Activating Token Index: 347

Text #3

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1638667 (Python Code)

Max Activating Token Index: 15

Text #4

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0416. Min Act: -0.0003

Data Index: 709616 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0404. Min Act: -0.0003

Data Index: 585945 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0412. Min Act: -0.0003

Data Index: 858080 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0392. Min Act: -0.0003

Data Index: 295622 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0387. Min Act: -0.0003

Data Index: 1186957 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0382. Min Act: -0.0003

Data Index: 760146 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0374. Min Act: -0.0003

Data Index: 1255872 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0383. Min Act: -0.0003

Data Index: 126954 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0366. Min Act: -0.0003

Data Index: 969408 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0388. Min Act: -0.0003

Data Index: 475462 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1196122 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0366. Min Act: -0.0003

Data Index: 622823 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0388. Min Act: -0.0003

Data Index: 396036 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0372. Min Act: -0.0003

Data Index: 1242672 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0392. Min Act: -0.0003

Data Index: 967172 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1527128 (Python Code)

Max Activating Token Index: 22