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

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

Neuron 3535 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: 0.1108. Min Range: -0.1108

Max Act: 0.1108. Min Act: -0.0002

Data Index: 1244964 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0892. Min Act: -0.0002

Data Index: 311755 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0808. Min Act: -0.0002

Data Index: 609223 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0766. Min Act: -0.0002

Data Index: 874750 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1219593 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1379609 (Python Code)

Max Activating Token Index: 858

Text #6

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1465261 (Python Code)

Max Activating Token Index: 957

Text #7

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0705. Min Act: -0.0002

Data Index: 604868 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1464305 (Python Code)

Max Activating Token Index: 767

Text #9

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0723. Min Act: -0.0002

Data Index: 644747 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1533394 (Python Code)

Max Activating Token Index: 280

Text #11

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0693. Min Act: -0.0002

Data Index: 227216 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0699. Min Act: -0.0002

Data Index: 423141 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1511494 (Python Code)

Max Activating Token Index: 622

Text #14

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0701. Min Act: -0.0002

Data Index: 503435 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0697. Min Act: -0.0002

Data Index: 421336 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1471003 (Python Code)

Max Activating Token Index: 905

Text #17

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1617455 (Python Code)

Max Activating Token Index: 76

Text #18

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0682. Min Act: -0.0002

Data Index: 586914 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1547143 (Python Code)

Max Activating Token Index: 730