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

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

Neuron 339 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.7607. Min Act: -0.0001

Data Index: 1544252 (Python Code)

Max Activating Token Index: 756

Text #1

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.7635. Min Act: -0.0001

Data Index: 1443549 (Python Code)

Max Activating Token Index: 58

Text #2

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.7248. Min Act: -0.0001

Data Index: 1515022 (Python Code)

Max Activating Token Index: 47

Text #3

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6484. Min Act: -0.0001

Data Index: 1646706 (Python Code)

Max Activating Token Index: 395

Text #4

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6487. Min Act: -0.0001

Data Index: 1604438 (Python Code)

Max Activating Token Index: 778

Text #5

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6385. Min Act: -0.0001

Data Index: 1539292 (Python Code)

Max Activating Token Index: 523

Text #6

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6001. Min Act: -0.0001

Data Index: 1623950 (Python Code)

Max Activating Token Index: 762

Text #7

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6293. Min Act: -0.0001

Data Index: 1557815 (Python Code)

Max Activating Token Index: 241

Text #8

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6273. Min Act: -0.0001

Data Index: 1513850 (Python Code)

Max Activating Token Index: 874

Text #9

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6210. Min Act: -0.0001

Data Index: 1493711 (Python Code)

Max Activating Token Index: 382

Text #10

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6120. Min Act: -0.0001

Data Index: 1511804 (Python Code)

Max Activating Token Index: 120

Text #11

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5713. Min Act: -0.0001

Data Index: 1547284 (Python Code)

Max Activating Token Index: 505

Text #12

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5909. Min Act: -0.0001

Data Index: 1631633 (Python Code)

Max Activating Token Index: 419

Text #13

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5850. Min Act: -0.0001

Data Index: 1365186 (Python Code)

Max Activating Token Index: 755

Text #14

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5609. Min Act: -0.0001

Data Index: 1461255 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5955. Min Act: -0.0001

Data Index: 1648617 (Python Code)

Max Activating Token Index: 250

Text #16

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5395. Min Act: -0.0001

Data Index: 1498924 (Python Code)

Max Activating Token Index: 323

Text #17

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5814. Min Act: -0.0001

Data Index: 1634464 (Python Code)

Max Activating Token Index: 158

Text #18

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5559. Min Act: -0.0001

Data Index: 1622371 (Python Code)

Max Activating Token Index: 816

Text #19

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5564. Min Act: -0.0001

Data Index: 1598769 (Python Code)

Max Activating Token Index: 318