Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2971 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1332. Min Act: -0.0001

Data Index: 922508 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1142. Min Act: -0.0001

Data Index: 751117 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1023. Min Act: -0.0000

Data Index: 619456 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1056. Min Act: -0.0001

Data Index: 965887 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0990. Min Act: -0.0001

Data Index: 550954 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0997. Min Act: -0.0001

Data Index: 279724 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0958. Min Act: -0.0001

Data Index: 545769 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0906. Min Act: -0.0001

Data Index: 519221 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0836. Min Act: -0.0000

Data Index: 474430 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0896. Min Act: -0.0001

Data Index: 706530 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0846. Min Act: -0.0001

Data Index: 791221 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0834. Min Act: -0.0001

Data Index: 902228 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0838. Min Act: -0.0001

Data Index: 251939 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0817. Min Act: -0.0001

Data Index: 984929 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0815. Min Act: -0.0001

Data Index: 369940 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0738. Min Act: -0.0001

Data Index: 1292200 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0753. Min Act: -0.0001

Data Index: 504033 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0704. Min Act: -0.0001

Data Index: 984293 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0711. Min Act: -0.0001

Data Index: 679828 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1339330 (C4 (Web Text))

Max Activating Token Index: 678