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

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

Neuron 2761 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: 0.9740. Min Range: -0.9740

Max Act: 0.9740. Min Act: -0.0002

Data Index: 987441 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.9740. Min Range: -0.9740

Max Act: 0.9657. Min Act: -0.0002

Data Index: 1080523 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.9740. Min Range: -0.9740

Max Act: 0.9550. Min Act: -0.0002

Data Index: 19562 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.9740. Min Range: -0.9740

Max Act: 0.9689. Min Act: -0.0002

Data Index: 431903 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.9740. Min Range: -0.9740

Max Act: 0.9415. Min Act: -0.0002

Data Index: 50205 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.9740. Min Range: -0.9740

Max Act: 0.9416. Min Act: -0.0002

Data Index: 735487 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.9740. Min Range: -0.9740

Max Act: 0.9261. Min Act: -0.0002

Data Index: 374538 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.9740. Min Range: -0.9740

Max Act: 0.9060. Min Act: -0.0002

Data Index: 602945 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.9740. Min Range: -0.9740

Max Act: 0.9007. Min Act: -0.0002

Data Index: 702243 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.9740. Min Range: -0.9740

Max Act: 0.8838. Min Act: -0.0002

Data Index: 760734 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 0.9740. Min Range: -0.9740

Max Act: 0.8917. Min Act: -0.0002

Data Index: 1272043 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.9740. Min Range: -0.9740

Max Act: 0.8721. Min Act: -0.0002

Data Index: 439336 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.9740. Min Range: -0.9740

Max Act: 0.8651. Min Act: -0.0002

Data Index: 1286455 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.9740. Min Range: -0.9740

Max Act: 0.8719. Min Act: -0.0002

Data Index: 20271 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.9740. Min Range: -0.9740

Max Act: 0.8591. Min Act: -0.0002

Data Index: 590396 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.9740. Min Range: -0.9740

Max Act: 0.8622. Min Act: -0.0002

Data Index: 145094 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.9740. Min Range: -0.9740

Max Act: 0.8757. Min Act: -0.0002

Data Index: 1116179 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.9740. Min Range: -0.9740

Max Act: 0.8756. Min Act: -0.0002

Data Index: 670713 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.9740. Min Range: -0.9740

Max Act: 0.8496. Min Act: -0.0002

Data Index: 742573 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.9740. Min Range: -0.9740

Max Act: 0.8487. Min Act: -0.0002

Data Index: 839 (C4 (Web Text))

Max Activating Token Index: 272