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

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

Neuron 5980 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6226. Min Range: -2.6226

Max Act: 2.6226. Min Act: -0.0000

Data Index: 1574104 (Python Code)

Max Activating Token Index: 580

Text #1

Max Range: 2.6226. Min Range: -2.6226

Max Act: 1.2638. Min Act: -0.0000

Data Index: 1588872 (Python Code)

Max Activating Token Index: 492

Text #2

Max Range: 2.6226. Min Range: -2.6226

Max Act: 1.3266. Min Act: -0.0000

Data Index: 1550727 (Python Code)

Max Activating Token Index: 188

Text #3

Max Range: 2.6226. Min Range: -2.6226

Max Act: 1.1483. Min Act: -0.0000

Data Index: 1610139 (Python Code)

Max Activating Token Index: 868

Text #4

Max Range: 2.6226. Min Range: -2.6226

Max Act: 1.2047. Min Act: -0.0000

Data Index: 1378405 (Python Code)

Max Activating Token Index: 486

Text #5

Max Range: 2.6226. Min Range: -2.6226

Max Act: 1.1245. Min Act: -0.0000

Data Index: 1651895 (Python Code)

Max Activating Token Index: 762

Text #6

Max Range: 2.6226. Min Range: -2.6226

Max Act: 1.1389. Min Act: -0.0000

Data Index: 1394947 (Python Code)

Max Activating Token Index: 500

Text #7

Max Range: 2.6226. Min Range: -2.6226

Max Act: 1.1030. Min Act: -0.0000

Data Index: 1420818 (Python Code)

Max Activating Token Index: 995

Text #8

Max Range: 2.6226. Min Range: -2.6226

Max Act: 1.1233. Min Act: -0.0000

Data Index: 1614559 (Python Code)

Max Activating Token Index: 691

Text #9

Max Range: 2.6226. Min Range: -2.6226

Max Act: 1.1404. Min Act: -0.0000

Data Index: 1646716 (Python Code)

Max Activating Token Index: 430

Text #10

Max Range: 2.6226. Min Range: -2.6226

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1529234 (Python Code)

Max Activating Token Index: 182

Text #11

Max Range: 2.6226. Min Range: -2.6226

Max Act: 1.0609. Min Act: -0.0000

Data Index: 1470268 (Python Code)

Max Activating Token Index: 168

Text #12

Max Range: 2.6226. Min Range: -2.6226

Max Act: 1.0960. Min Act: -0.0000

Data Index: 1500194 (Python Code)

Max Activating Token Index: 710

Text #13

Max Range: 2.6226. Min Range: -2.6226

Max Act: 1.0364. Min Act: -0.0000

Data Index: 1476200 (Python Code)

Max Activating Token Index: 173

Text #14

Max Range: 2.6226. Min Range: -2.6226

Max Act: 1.0035. Min Act: -0.0000

Data Index: 1548299 (Python Code)

Max Activating Token Index: 528

Text #15

Max Range: 2.6226. Min Range: -2.6226

Max Act: 1.0313. Min Act: -0.0000

Data Index: 1374448 (Python Code)

Max Activating Token Index: 217

Text #16

Max Range: 2.6226. Min Range: -2.6226

Max Act: 0.9030. Min Act: -0.0000

Data Index: 1557685 (Python Code)

Max Activating Token Index: 246

Text #17

Max Range: 2.6226. Min Range: -2.6226

Max Act: 0.9113. Min Act: -0.0000

Data Index: 1403529 (Python Code)

Max Activating Token Index: 169

Text #18

Max Range: 2.6226. Min Range: -2.6226

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1556109 (Python Code)

Max Activating Token Index: 840

Text #19

Max Range: 2.6226. Min Range: -2.6226

Max Act: 0.9226. Min Act: -0.0000

Data Index: 1493634 (Python Code)

Max Activating Token Index: 70