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

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

Neuron 1774 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0710. Min Act: -0.0002

Data Index: 1410859 (Python Code)

Max Activating Token Index: 751

Text #1

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1413143 (Python Code)

Max Activating Token Index: 254

Text #2

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1466618 (Python Code)

Max Activating Token Index: 367

Text #3

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1617018 (Python Code)

Max Activating Token Index: 557

Text #4

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1545049 (Python Code)

Max Activating Token Index: 368

Text #5

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1493257 (Python Code)

Max Activating Token Index: 384

Text #6

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1416361 (Python Code)

Max Activating Token Index: 30

Text #7

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1643754 (Python Code)

Max Activating Token Index: 897

Text #8

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1559504 (Python Code)

Max Activating Token Index: 85

Text #9

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1498543 (Python Code)

Max Activating Token Index: 21

Text #10

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1482490 (Python Code)

Max Activating Token Index: 240

Text #11

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1506828 (Python Code)

Max Activating Token Index: 165

Text #12

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1651557 (Python Code)

Max Activating Token Index: 165

Text #13

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1538537 (Python Code)

Max Activating Token Index: 347

Text #14

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1403113 (Python Code)

Max Activating Token Index: 393

Text #15

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1605695 (Python Code)

Max Activating Token Index: 83

Text #16

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1385457 (Python Code)

Max Activating Token Index: 205

Text #17

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1616677 (Python Code)

Max Activating Token Index: 588

Text #18

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1594514 (Python Code)

Max Activating Token Index: 43

Text #19

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1414940 (Python Code)

Max Activating Token Index: 206