Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2967 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1574684 (Python Code)

Max Activating Token Index: 60

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0438. Min Act: -0.0003

Data Index: 1376820 (Python Code)

Max Activating Token Index: 20

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0389. Min Act: -0.0003

Data Index: 1527478 (Python Code)

Max Activating Token Index: 214

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0392. Min Act: -0.0003

Data Index: 1563418 (Python Code)

Max Activating Token Index: 297

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0370. Min Act: -0.0003

Data Index: 1435138 (Python Code)

Max Activating Token Index: 283

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1621057 (Python Code)

Max Activating Token Index: 783

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1624173 (Python Code)

Max Activating Token Index: 343

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0372. Min Act: -0.0003

Data Index: 1513869 (Python Code)

Max Activating Token Index: 647

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0362. Min Act: -0.0003

Data Index: 1398244 (Python Code)

Max Activating Token Index: 918

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1383809 (Python Code)

Max Activating Token Index: 304

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0352. Min Act: -0.0003

Data Index: 1385780 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0380. Min Act: -0.0003

Data Index: 1591884 (Python Code)

Max Activating Token Index: 218

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1413984 (Python Code)

Max Activating Token Index: 315

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1412905 (Python Code)

Max Activating Token Index: 81

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0346. Min Act: -0.0003

Data Index: 1373892 (Python Code)

Max Activating Token Index: 237

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0352. Min Act: -0.0003

Data Index: 1510364 (Python Code)

Max Activating Token Index: 217

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0344. Min Act: -0.0003

Data Index: 1504871 (Python Code)

Max Activating Token Index: 293

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0352. Min Act: -0.0003

Data Index: 1549431 (Python Code)

Max Activating Token Index: 457

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0350. Min Act: -0.0003

Data Index: 1480258 (Python Code)

Max Activating Token Index: 54

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1370831 (Python Code)

Max Activating Token Index: 684