Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2518 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0363. Min Act: -0.0004

Data Index: 1576659 (Python Code)

Max Activating Token Index: 199

Text #1

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0364. Min Act: -0.0004

Data Index: 1484536 (Python Code)

Max Activating Token Index: 546

Text #2

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0324. Min Act: -0.0004

Data Index: 1585665 (Python Code)

Max Activating Token Index: 800

Text #3

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0316. Min Act: -0.0004

Data Index: 1466149 (Python Code)

Max Activating Token Index: 298

Text #4

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0359. Min Act: -0.0004

Data Index: 1473275 (Python Code)

Max Activating Token Index: 301

Text #5

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0360. Min Act: -0.0004

Data Index: 1512292 (Python Code)

Max Activating Token Index: 157

Text #6

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0328. Min Act: -0.0004

Data Index: 1478798 (Python Code)

Max Activating Token Index: 936

Text #7

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0344. Min Act: -0.0004

Data Index: 1613243 (Python Code)

Max Activating Token Index: 475

Text #8

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0379. Min Act: -0.0004

Data Index: 1502540 (Python Code)

Max Activating Token Index: 818

Text #9

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0322. Min Act: -0.0004

Data Index: 1647683 (Python Code)

Max Activating Token Index: 239

Text #10

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0308. Min Act: -0.0004

Data Index: 1468011 (Python Code)

Max Activating Token Index: 633

Text #11

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0334. Min Act: -0.0004

Data Index: 1403198 (Python Code)

Max Activating Token Index: 484

Text #12

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0356. Min Act: -0.0004

Data Index: 1375733 (Python Code)

Max Activating Token Index: 272

Text #13

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0334. Min Act: -0.0004

Data Index: 1576792 (Python Code)

Max Activating Token Index: 734

Text #14

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0314. Min Act: -0.0004

Data Index: 1491324 (Python Code)

Max Activating Token Index: 150

Text #15

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0330. Min Act: -0.0004

Data Index: 1388935 (Python Code)

Max Activating Token Index: 157

Text #16

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0324. Min Act: -0.0004

Data Index: 1424334 (Python Code)

Max Activating Token Index: 206

Text #17

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0331. Min Act: -0.0004

Data Index: 1569934 (Python Code)

Max Activating Token Index: 123

Text #18

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0337. Min Act: -0.0004

Data Index: 1482462 (Python Code)

Max Activating Token Index: 162

Text #19

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0308. Min Act: -0.0004

Data Index: 1414507 (Python Code)

Max Activating Token Index: 878