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

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

Neuron 5949 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0097. Min Act: -0.0001

Data Index: 1585160 (Python Code)

Max Activating Token Index: 382

Text #1

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0094. Min Act: -0.0001

Data Index: 1447092 (Python Code)

Max Activating Token Index: 284

Text #2

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0096. Min Act: -0.0001

Data Index: 1523696 (Python Code)

Max Activating Token Index: 678

Text #3

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0095. Min Act: -0.0001

Data Index: 1574752 (Python Code)

Max Activating Token Index: 517

Text #4

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0093. Min Act: -0.0001

Data Index: 1553906 (Python Code)

Max Activating Token Index: 396

Text #5

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0093. Min Act: -0.0001

Data Index: 1402908 (Python Code)

Max Activating Token Index: 438

Text #6

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0094. Min Act: -0.0001

Data Index: 1468024 (Python Code)

Max Activating Token Index: 768

Text #7

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0092. Min Act: -0.0001

Data Index: 1567596 (Python Code)

Max Activating Token Index: 248

Text #8

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0092. Min Act: -0.0001

Data Index: 1556612 (Python Code)

Max Activating Token Index: 412

Text #9

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0091. Min Act: -0.0001

Data Index: 1520361 (Python Code)

Max Activating Token Index: 396

Text #10

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0092. Min Act: -0.0001

Data Index: 1488817 (Python Code)

Max Activating Token Index: 314

Text #11

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0092. Min Act: -0.0001

Data Index: 1600283 (Python Code)

Max Activating Token Index: 356

Text #12

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0090. Min Act: -0.0001

Data Index: 1372339 (Python Code)

Max Activating Token Index: 625

Text #13

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0090. Min Act: -0.0001

Data Index: 1541970 (Python Code)

Max Activating Token Index: 540

Text #14

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1639739 (Python Code)

Max Activating Token Index: 414

Text #15

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0089. Min Act: -0.0001

Data Index: 1606775 (Python Code)

Max Activating Token Index: 489

Text #16

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0089. Min Act: -0.0001

Data Index: 1571889 (Python Code)

Max Activating Token Index: 301

Text #17

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0090. Min Act: -0.0001

Data Index: 1475374 (Python Code)

Max Activating Token Index: 375

Text #18

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0090. Min Act: -0.0001

Data Index: 1389632 (Python Code)

Max Activating Token Index: 382

Text #19

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0090. Min Act: -0.0001

Data Index: 1514172 (Python Code)

Max Activating Token Index: 174