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

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

Neuron 4082 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8256. Min Range: -2.8256

Max Act: 2.8256. Min Act: -0.0000

Data Index: 1372643 (Python Code)

Max Activating Token Index: 343

Text #1

Max Range: 2.8256. Min Range: -2.8256

Max Act: 2.8097. Min Act: -0.0000

Data Index: 1556894 (Python Code)

Max Activating Token Index: 260

Text #2

Max Range: 2.8256. Min Range: -2.8256

Max Act: 2.7518. Min Act: -0.0000

Data Index: 1552689 (Python Code)

Max Activating Token Index: 362

Text #3

Max Range: 2.8256. Min Range: -2.8256

Max Act: 2.2944. Min Act: -0.0000

Data Index: 1366616 (Python Code)

Max Activating Token Index: 355

Text #4

Max Range: 2.8256. Min Range: -2.8256

Max Act: 2.5287. Min Act: -0.0000

Data Index: 1386577 (Python Code)

Max Activating Token Index: 243

Text #5

Max Range: 2.8256. Min Range: -2.8256

Max Act: 2.7104. Min Act: -0.0000

Data Index: 1555683 (Python Code)

Max Activating Token Index: 259

Text #6

Max Range: 2.8256. Min Range: -2.8256

Max Act: 2.0536. Min Act: -0.0000

Data Index: 1563798 (Python Code)

Max Activating Token Index: 290

Text #7

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.9311. Min Act: -0.0000

Data Index: 1631464 (Python Code)

Max Activating Token Index: 90

Text #8

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.9535. Min Act: -0.0000

Data Index: 1526030 (Python Code)

Max Activating Token Index: 144

Text #9

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.7736. Min Act: -0.0000

Data Index: 1545974 (Python Code)

Max Activating Token Index: 315

Text #10

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.8694. Min Act: -0.0000

Data Index: 1556816 (Python Code)

Max Activating Token Index: 473

Text #11

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.6384. Min Act: -0.0000

Data Index: 1456553 (Python Code)

Max Activating Token Index: 216

Text #12

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.9275. Min Act: -0.0000

Data Index: 1486668 (Python Code)

Max Activating Token Index: 478

Text #13

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.7274. Min Act: -0.0000

Data Index: 1481683 (Python Code)

Max Activating Token Index: 109

Text #14

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.6149. Min Act: -0.0000

Data Index: 1632252 (Python Code)

Max Activating Token Index: 527

Text #15

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.6706. Min Act: -0.0000

Data Index: 1420677 (Python Code)

Max Activating Token Index: 305

Text #16

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.6346. Min Act: -0.0000

Data Index: 1642430 (Python Code)

Max Activating Token Index: 239

Text #17

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.4452. Min Act: -0.0000

Data Index: 1377976 (Python Code)

Max Activating Token Index: 48

Text #18

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.8298. Min Act: -0.0000

Data Index: 1585792 (Python Code)

Max Activating Token Index: 297

Text #19

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.5823. Min Act: -0.0000

Data Index: 1633783 (Python Code)

Max Activating Token Index: 95