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

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

Neuron 1571 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6218. Min Range: -3.6218

Max Act: 3.4122. Min Act: -0.0000

Data Index: 1475770 (Python Code)

Max Activating Token Index: 527

Text #1

Max Range: 3.6218. Min Range: -3.6218

Max Act: 3.6218. Min Act: -0.0000

Data Index: 1553885 (Python Code)

Max Activating Token Index: 816

Text #2

Max Range: 3.6218. Min Range: -3.6218

Max Act: 3.1355. Min Act: -0.0000

Data Index: 1509832 (Python Code)

Max Activating Token Index: 108

Text #3

Max Range: 3.6218. Min Range: -3.6218

Max Act: 3.0815. Min Act: -0.0000

Data Index: 1502591 (Python Code)

Max Activating Token Index: 213

Text #4

Max Range: 3.6218. Min Range: -3.6218

Max Act: 3.0123. Min Act: -0.0000

Data Index: 1568642 (Python Code)

Max Activating Token Index: 191

Text #5

Max Range: 3.6218. Min Range: -3.6218

Max Act: 2.8328. Min Act: -0.0000

Data Index: 1376888 (Python Code)

Max Activating Token Index: 229

Text #6

Max Range: 3.6218. Min Range: -3.6218

Max Act: 2.8645. Min Act: -0.0000

Data Index: 1383396 (Python Code)

Max Activating Token Index: 452

Text #7

Max Range: 3.6218. Min Range: -3.6218

Max Act: 2.8508. Min Act: -0.0000

Data Index: 1609021 (Python Code)

Max Activating Token Index: 728

Text #8

Max Range: 3.6218. Min Range: -3.6218

Max Act: 2.7387. Min Act: -0.0000

Data Index: 1378129 (Python Code)

Max Activating Token Index: 558

Text #9

Max Range: 3.6218. Min Range: -3.6218

Max Act: 2.6029. Min Act: -0.0000

Data Index: 1405978 (Python Code)

Max Activating Token Index: 590

Text #10

Max Range: 3.6218. Min Range: -3.6218

Max Act: 2.6132. Min Act: -0.0000

Data Index: 555062 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 3.6218. Min Range: -3.6218

Max Act: 2.4315. Min Act: -0.0000

Data Index: 1384134 (Python Code)

Max Activating Token Index: 963

Text #12

Max Range: 3.6218. Min Range: -3.6218

Max Act: 2.4147. Min Act: -0.0000

Data Index: 1623950 (Python Code)

Max Activating Token Index: 574

Text #13

Max Range: 3.6218. Min Range: -3.6218

Max Act: 2.5261. Min Act: -0.0000

Data Index: 1573337 (Python Code)

Max Activating Token Index: 783

Text #14

Max Range: 3.6218. Min Range: -3.6218

Max Act: 2.4023. Min Act: -0.0000

Data Index: 1365186 (Python Code)

Max Activating Token Index: 559

Text #15

Max Range: 3.6218. Min Range: -3.6218

Max Act: 2.6383. Min Act: -0.0000

Data Index: 1491546 (Python Code)

Max Activating Token Index: 639

Text #16

Max Range: 3.6218. Min Range: -3.6218

Max Act: 2.4644. Min Act: -0.0000

Data Index: 1556177 (Python Code)

Max Activating Token Index: 233

Text #17

Max Range: 3.6218. Min Range: -3.6218

Max Act: 2.2831. Min Act: -0.0000

Data Index: 1631633 (Python Code)

Max Activating Token Index: 242

Text #18

Max Range: 3.6218. Min Range: -3.6218

Max Act: 2.2905. Min Act: -0.0000

Data Index: 1517412 (Python Code)

Max Activating Token Index: 295

Text #19

Max Range: 3.6218. Min Range: -3.6218

Max Act: 2.3522. Min Act: -0.0000

Data Index: 1472464 (Python Code)

Max Activating Token Index: 715