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

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

Neuron 1968 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: 0.2916. Min Range: -0.2916

Max Act: 0.2916. Min Act: -0.0002

Data Index: 1414005 (Python Code)

Max Activating Token Index: 560

Text #1

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2854. Min Act: -0.0002

Data Index: 1588660 (Python Code)

Max Activating Token Index: 379

Text #2

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2841. Min Act: -0.0002

Data Index: 1369284 (Python Code)

Max Activating Token Index: 192

Text #3

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2759. Min Act: -0.0002

Data Index: 1554288 (Python Code)

Max Activating Token Index: 337

Text #4

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2737. Min Act: -0.0002

Data Index: 1373588 (Python Code)

Max Activating Token Index: 298

Text #5

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2705. Min Act: -0.0002

Data Index: 1619683 (Python Code)

Max Activating Token Index: 465

Text #6

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2695. Min Act: -0.0002

Data Index: 1574217 (Python Code)

Max Activating Token Index: 972

Text #7

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2738. Min Act: -0.0002

Data Index: 1537000 (Python Code)

Max Activating Token Index: 43

Text #8

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2669. Min Act: -0.0002

Data Index: 1371043 (Python Code)

Max Activating Token Index: 731

Text #9

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2628. Min Act: -0.0002

Data Index: 1634545 (Python Code)

Max Activating Token Index: 913

Text #10

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2604. Min Act: -0.0002

Data Index: 1568295 (Python Code)

Max Activating Token Index: 769

Text #11

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2606. Min Act: -0.0002

Data Index: 1566933 (Python Code)

Max Activating Token Index: 442

Text #12

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2650. Min Act: -0.0002

Data Index: 1631976 (Python Code)

Max Activating Token Index: 624

Text #13

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2654. Min Act: -0.0002

Data Index: 1527899 (Python Code)

Max Activating Token Index: 550

Text #14

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2641. Min Act: -0.0002

Data Index: 1627161 (Python Code)

Max Activating Token Index: 298

Text #15

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2608. Min Act: -0.0002

Data Index: 1597957 (Python Code)

Max Activating Token Index: 179

Text #16

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2564. Min Act: -0.0002

Data Index: 1582788 (Python Code)

Max Activating Token Index: 931

Text #17

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2608. Min Act: -0.0002

Data Index: 1362699 (Python Code)

Max Activating Token Index: 115

Text #18

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2549. Min Act: -0.0002

Data Index: 1523011 (Python Code)

Max Activating Token Index: 127

Text #19

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2596. Min Act: -0.0002

Data Index: 1449938 (Python Code)

Max Activating Token Index: 367