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

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

Neuron 4754 in Layer 1

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: 0.0691. Min Range: -0.0691

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1482824 (Python Code)

Max Activating Token Index: 124

Text #1

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1609846 (Python Code)

Max Activating Token Index: 995

Text #2

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0618. Min Act: -0.0003

Data Index: 191203 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1619807 (Python Code)

Max Activating Token Index: 86

Text #4

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1578666 (Python Code)

Max Activating Token Index: 453

Text #5

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0606. Min Act: -0.0002

Data Index: 667688 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1483031 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1543088 (Python Code)

Max Activating Token Index: 246

Text #8

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1352094 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1591875 (Python Code)

Max Activating Token Index: 997

Text #10

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1597831 (Python Code)

Max Activating Token Index: 1014

Text #11

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1628165 (Python Code)

Max Activating Token Index: 1007

Text #12

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1418984 (Python Code)

Max Activating Token Index: 32

Text #13

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1458107 (Python Code)

Max Activating Token Index: 80

Text #14

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1525935 (Python Code)

Max Activating Token Index: 930

Text #15

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1519021 (Python Code)

Max Activating Token Index: 8

Text #16

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1481086 (Python Code)

Max Activating Token Index: 285

Text #17

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1481090 (Python Code)

Max Activating Token Index: 547

Text #18

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1615770 (Python Code)

Max Activating Token Index: 211

Text #19

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1315685 (C4 (Web Text))

Max Activating Token Index: 413