Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3433 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.0079. Min Range: -5.0079

Max Act: 5.0079. Min Act: -0.0000

Data Index: 1476459 (Python Code)

Max Activating Token Index: 810

Text #1

Max Range: 5.0079. Min Range: -5.0079

Max Act: 4.7457. Min Act: -0.0001

Data Index: 1585615 (Python Code)

Max Activating Token Index: 786

Text #2

Max Range: 5.0079. Min Range: -5.0079

Max Act: 4.5372. Min Act: -0.0000

Data Index: 1370537 (Python Code)

Max Activating Token Index: 40

Text #3

Max Range: 5.0079. Min Range: -5.0079

Max Act: 4.1343. Min Act: -0.0001

Data Index: 1364078 (Python Code)

Max Activating Token Index: 526

Text #4

Max Range: 5.0079. Min Range: -5.0079

Max Act: 4.2192. Min Act: -0.0000

Data Index: 1451220 (Python Code)

Max Activating Token Index: 494

Text #5

Max Range: 5.0079. Min Range: -5.0079

Max Act: 4.1840. Min Act: -0.0001

Data Index: 1518978 (Python Code)

Max Activating Token Index: 287

Text #6

Max Range: 5.0079. Min Range: -5.0079

Max Act: 3.7558. Min Act: -0.0000

Data Index: 1509126 (Python Code)

Max Activating Token Index: 894

Text #7

Max Range: 5.0079. Min Range: -5.0079

Max Act: 3.7651. Min Act: -0.0000

Data Index: 1622437 (Python Code)

Max Activating Token Index: 39

Text #8

Max Range: 5.0079. Min Range: -5.0079

Max Act: 3.6991. Min Act: -0.0000

Data Index: 1404777 (Python Code)

Max Activating Token Index: 521

Text #9

Max Range: 5.0079. Min Range: -5.0079

Max Act: 3.5910. Min Act: -0.0001

Data Index: 1557330 (Python Code)

Max Activating Token Index: 744

Text #10

Max Range: 5.0079. Min Range: -5.0079

Max Act: 3.0407. Min Act: -0.0000

Data Index: 1463061 (Python Code)

Max Activating Token Index: 188

Text #11

Max Range: 5.0079. Min Range: -5.0079

Max Act: 3.4664. Min Act: -0.0000

Data Index: 1473437 (Python Code)

Max Activating Token Index: 414

Text #12

Max Range: 5.0079. Min Range: -5.0079

Max Act: 3.2510. Min Act: -0.0000

Data Index: 1507010 (Python Code)

Max Activating Token Index: 839

Text #13

Max Range: 5.0079. Min Range: -5.0079

Max Act: 3.2031. Min Act: -0.0000

Data Index: 1468555 (Python Code)

Max Activating Token Index: 867

Text #14

Max Range: 5.0079. Min Range: -5.0079

Max Act: 3.3433. Min Act: -0.0001

Data Index: 1433221 (Python Code)

Max Activating Token Index: 110

Text #15

Max Range: 5.0079. Min Range: -5.0079

Max Act: 3.4903. Min Act: -0.0001

Data Index: 1632370 (Python Code)

Max Activating Token Index: 914

Text #16

Max Range: 5.0079. Min Range: -5.0079

Max Act: 3.4353. Min Act: -0.0001

Data Index: 1592398 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 5.0079. Min Range: -5.0079

Max Act: 3.1339. Min Act: -0.0000

Data Index: 1494143 (Python Code)

Max Activating Token Index: 140

Text #18

Max Range: 5.0079. Min Range: -5.0079

Max Act: 3.5907. Min Act: -0.0001

Data Index: 1460662 (Python Code)

Max Activating Token Index: 980

Text #19

Max Range: 5.0079. Min Range: -5.0079

Max Act: 3.1188. Min Act: -0.0000

Data Index: 1638273 (Python Code)

Max Activating Token Index: 310