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

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

Neuron 3926 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: 2.5424. Min Range: -2.5424

Max Act: 2.5424. Min Act: -0.0000

Data Index: 1629089 (Python Code)

Max Activating Token Index: 477

Text #1

Max Range: 2.5424. Min Range: -2.5424

Max Act: 2.4109. Min Act: -0.0000

Data Index: 1521757 (Python Code)

Max Activating Token Index: 763

Text #2

Max Range: 2.5424. Min Range: -2.5424

Max Act: 1.5977. Min Act: -0.0000

Data Index: 1481293 (Python Code)

Max Activating Token Index: 266

Text #3

Max Range: 2.5424. Min Range: -2.5424

Max Act: 1.4248. Min Act: -0.0000

Data Index: 1654514 (Python Code)

Max Activating Token Index: 171

Text #4

Max Range: 2.5424. Min Range: -2.5424

Max Act: 1.4198. Min Act: -0.0000

Data Index: 1440255 (Python Code)

Max Activating Token Index: 355

Text #5

Max Range: 2.5424. Min Range: -2.5424

Max Act: 1.3634. Min Act: -0.0000

Data Index: 1625115 (Python Code)

Max Activating Token Index: 710

Text #6

Max Range: 2.5424. Min Range: -2.5424

Max Act: 1.2642. Min Act: -0.0000

Data Index: 1539168 (Python Code)

Max Activating Token Index: 419

Text #7

Max Range: 2.5424. Min Range: -2.5424

Max Act: 1.2376. Min Act: -0.0000

Data Index: 1473356 (Python Code)

Max Activating Token Index: 404

Text #8

Max Range: 2.5424. Min Range: -2.5424

Max Act: 1.2222. Min Act: -0.0000

Data Index: 1431207 (Python Code)

Max Activating Token Index: 540

Text #9

Max Range: 2.5424. Min Range: -2.5424

Max Act: 1.2114. Min Act: -0.0000

Data Index: 1551246 (Python Code)

Max Activating Token Index: 613

Text #10

Max Range: 2.5424. Min Range: -2.5424

Max Act: 1.0981. Min Act: -0.0000

Data Index: 1654820 (Python Code)

Max Activating Token Index: 693

Text #11

Max Range: 2.5424. Min Range: -2.5424

Max Act: 1.0495. Min Act: -0.0000

Data Index: 1449620 (Python Code)

Max Activating Token Index: 947

Text #12

Max Range: 2.5424. Min Range: -2.5424

Max Act: 1.2412. Min Act: -0.0000

Data Index: 1490586 (Python Code)

Max Activating Token Index: 346

Text #13

Max Range: 2.5424. Min Range: -2.5424

Max Act: 1.1883. Min Act: -0.0000

Data Index: 1426910 (Python Code)

Max Activating Token Index: 869

Text #14

Max Range: 2.5424. Min Range: -2.5424

Max Act: 1.1458. Min Act: -0.0000

Data Index: 1438851 (Python Code)

Max Activating Token Index: 535

Text #15

Max Range: 2.5424. Min Range: -2.5424

Max Act: 1.1107. Min Act: -0.0000

Data Index: 1433423 (Python Code)

Max Activating Token Index: 550

Text #16

Max Range: 2.5424. Min Range: -2.5424

Max Act: 1.0594. Min Act: -0.0000

Data Index: 1419204 (Python Code)

Max Activating Token Index: 292

Text #17

Max Range: 2.5424. Min Range: -2.5424

Max Act: 1.0883. Min Act: -0.0000

Data Index: 1634114 (Python Code)

Max Activating Token Index: 756

Text #18

Max Range: 2.5424. Min Range: -2.5424

Max Act: 1.0793. Min Act: -0.0000

Data Index: 1459114 (Python Code)

Max Activating Token Index: 520

Text #19

Max Range: 2.5424. Min Range: -2.5424

Max Act: 1.1037. Min Act: -0.0000

Data Index: 1446719 (Python Code)

Max Activating Token Index: 268