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

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

Neuron 163 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: 0.8032. Min Range: -0.8032

Max Act: 0.8032. Min Act: -0.0002

Data Index: 1585396 (Python Code)

Max Activating Token Index: 834

Text #1

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6996. Min Act: -0.0002

Data Index: 1498109 (Python Code)

Max Activating Token Index: 292

Text #2

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6522. Min Act: -0.0002

Data Index: 1633219 (Python Code)

Max Activating Token Index: 460

Text #3

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6405. Min Act: -0.0002

Data Index: 1543270 (Python Code)

Max Activating Token Index: 110

Text #4

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6090. Min Act: -0.0002

Data Index: 1573467 (Python Code)

Max Activating Token Index: 968

Text #5

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5985. Min Act: -0.0002

Data Index: 1411976 (Python Code)

Max Activating Token Index: 670

Text #6

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5989. Min Act: -0.0002

Data Index: 1632119 (Python Code)

Max Activating Token Index: 159

Text #7

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5871. Min Act: -0.0002

Data Index: 865602 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5837. Min Act: -0.0002

Data Index: 1594609 (Python Code)

Max Activating Token Index: 621

Text #9

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5738. Min Act: -0.0002

Data Index: 1515025 (Python Code)

Max Activating Token Index: 405

Text #10

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5830. Min Act: -0.0002

Data Index: 221718 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5787. Min Act: -0.0002

Data Index: 1621232 (Python Code)

Max Activating Token Index: 48

Text #12

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5627. Min Act: -0.0002

Data Index: 1636750 (Python Code)

Max Activating Token Index: 359

Text #13

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5616. Min Act: -0.0002

Data Index: 599130 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5522. Min Act: -0.0002

Data Index: 1423751 (Python Code)

Max Activating Token Index: 771

Text #15

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5520. Min Act: -0.0002

Data Index: 583052 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5366. Min Act: -0.0002

Data Index: 1521830 (Python Code)

Max Activating Token Index: 863

Text #17

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5412. Min Act: -0.0002

Data Index: 1553065 (Python Code)

Max Activating Token Index: 585

Text #18

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5520. Min Act: -0.0002

Data Index: 1383634 (Python Code)

Max Activating Token Index: 418

Text #19

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5430. Min Act: -0.0002

Data Index: 1231193 (C4 (Web Text))

Max Activating Token Index: 759