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

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

Neuron 1217 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: 0.1195. Min Range: -0.1195

Max Act: 0.1195. Min Act: -0.0002

Data Index: 1583759 (Python Code)

Max Activating Token Index: 947

Text #1

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1029. Min Act: -0.0002

Data Index: 1564451 (Python Code)

Max Activating Token Index: 703

Text #2

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1407458 (Python Code)

Max Activating Token Index: 963

Text #3

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1251311 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0946. Min Act: -0.0002

Data Index: 1134256 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0949. Min Act: -0.0002

Data Index: 349718 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0938. Min Act: -0.0002

Data Index: 865304 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0919. Min Act: -0.0002

Data Index: 222302 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0909. Min Act: -0.0002

Data Index: 663813 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1261586 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1293146 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0859. Min Act: -0.0002

Data Index: 1316684 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1374664 (Python Code)

Max Activating Token Index: 852

Text #13

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0849. Min Act: -0.0002

Data Index: 220627 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0865. Min Act: -0.0002

Data Index: 581438 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0843. Min Act: -0.0002

Data Index: 66369 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1429752 (Python Code)

Max Activating Token Index: 674

Text #17

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0834. Min Act: -0.0002

Data Index: 29491 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0826. Min Act: -0.0002

Data Index: 411446 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0846. Min Act: -0.0002

Data Index: 656092 (C4 (Web Text))

Max Activating Token Index: 115