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

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

Neuron 5117 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: 0.1066. Min Range: -0.1066

Max Act: 0.1066. Min Act: -0.0002

Data Index: 1093572 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0766. Min Act: -0.0002

Data Index: 322522 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0726. Min Act: -0.0002

Data Index: 59258 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1273928 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1649072 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0676. Min Act: -0.0002

Data Index: 30534 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1298876 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0529. Min Act: -0.0002

Data Index: 342074 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0538. Min Act: -0.0002

Data Index: 335531 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0547. Min Act: -0.0002

Data Index: 148998 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1540841 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1008355 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0510. Min Act: -0.0002

Data Index: 42585 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1595780 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0505. Min Act: -0.0002

Data Index: 942484 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1533745 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1192522 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0471. Min Act: -0.0002

Data Index: 38035 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0502. Min Act: -0.0002

Data Index: 143172 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1004838 (C4 (Web Text))

Max Activating Token Index: 1023