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

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

Neuron 1274 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: 1.4642. Min Range: -1.4642

Max Act: 1.4642. Min Act: -0.0000

Data Index: 1414654 (Python Code)

Max Activating Token Index: 271

Text #1

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.2533. Min Act: -0.0000

Data Index: 1392758 (Python Code)

Max Activating Token Index: 835

Text #2

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.2242. Min Act: -0.0000

Data Index: 1385044 (Python Code)

Max Activating Token Index: 226

Text #3

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.0458. Min Act: -0.0000

Data Index: 1634067 (Python Code)

Max Activating Token Index: 205

Text #4

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.1111. Min Act: -0.0000

Data Index: 1513823 (Python Code)

Max Activating Token Index: 494

Text #5

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.0867. Min Act: -0.0000

Data Index: 1480202 (Python Code)

Max Activating Token Index: 487

Text #6

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.1386. Min Act: -0.0000

Data Index: 1476412 (Python Code)

Max Activating Token Index: 490

Text #7

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.1171. Min Act: -0.0000

Data Index: 1548615 (Python Code)

Max Activating Token Index: 924

Text #8

Max Range: 1.4642. Min Range: -1.4642

Max Act: 0.9869. Min Act: -0.0000

Data Index: 1440407 (Python Code)

Max Activating Token Index: 494

Text #9

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.1199. Min Act: -0.0000

Data Index: 1527835 (Python Code)

Max Activating Token Index: 1015

Text #10

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.0682. Min Act: -0.0000

Data Index: 1360274 (Python Code)

Max Activating Token Index: 676

Text #11

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.1255. Min Act: -0.0000

Data Index: 1482036 (Python Code)

Max Activating Token Index: 656

Text #12

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1361656 (Python Code)

Max Activating Token Index: 141

Text #13

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1496659 (Python Code)

Max Activating Token Index: 187

Text #14

Max Range: 1.4642. Min Range: -1.4642

Max Act: 0.9784. Min Act: -0.0000

Data Index: 1473098 (Python Code)

Max Activating Token Index: 241

Text #15

Max Range: 1.4642. Min Range: -1.4642

Max Act: 1.1077. Min Act: -0.0000

Data Index: 1383504 (Python Code)

Max Activating Token Index: 313

Text #16

Max Range: 1.4642. Min Range: -1.4642

Max Act: 0.9354. Min Act: -0.0000

Data Index: 1469386 (Python Code)

Max Activating Token Index: 900

Text #17

Max Range: 1.4642. Min Range: -1.4642

Max Act: 0.9711. Min Act: -0.0000

Data Index: 1491944 (Python Code)

Max Activating Token Index: 750

Text #18

Max Range: 1.4642. Min Range: -1.4642

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1469545 (Python Code)

Max Activating Token Index: 924

Text #19

Max Range: 1.4642. Min Range: -1.4642

Max Act: 0.9213. Min Act: -0.0000

Data Index: 1621824 (Python Code)

Max Activating Token Index: 343