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

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

Neuron 5851 in Layer 0

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: 1.8925. Min Range: -1.8925

Max Act: 1.8878. Min Act: -0.0001

Data Index: 728475 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.8925. Min Act: -0.0001

Data Index: 1029091 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.8192. Min Act: -0.0001

Data Index: 2260 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.7841. Min Act: -0.0001

Data Index: 918968 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.7867. Min Act: -0.0001

Data Index: 439145 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.8026. Min Act: -0.0001

Data Index: 1079288 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.7607. Min Act: -0.0002

Data Index: 477599 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.7959. Min Act: -0.0001

Data Index: 1295911 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.8007. Min Act: -0.0002

Data Index: 22791 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.7577. Min Act: -0.0002

Data Index: 24633 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.7641. Min Act: -0.0001

Data Index: 735713 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.7942. Min Act: -0.0001

Data Index: 1142775 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.7876. Min Act: -0.0001

Data Index: 307986 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.7570. Min Act: -0.0001

Data Index: 1259075 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.7513. Min Act: -0.0001

Data Index: 1048689 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.7562. Min Act: -0.0001

Data Index: 1077910 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.7619. Min Act: -0.0002

Data Index: 382461 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.7729. Min Act: -0.0001

Data Index: 779787 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.7353. Min Act: -0.0001

Data Index: 883213 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.7361. Min Act: -0.0001

Data Index: 773730 (C4 (Web Text))

Max Activating Token Index: 1023