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

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

Neuron 3636 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: 1.2338. Min Range: -1.2338

Max Act: 1.2338. Min Act: -0.0001

Data Index: 1600766 (Python Code)

Max Activating Token Index: 591

Text #1

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.1946. Min Act: -0.0001

Data Index: 1614157 (Python Code)

Max Activating Token Index: 706

Text #2

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.1292. Min Act: -0.0001

Data Index: 1500809 (Python Code)

Max Activating Token Index: 915

Text #3

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.1186. Min Act: -0.0002

Data Index: 1404722 (Python Code)

Max Activating Token Index: 742

Text #4

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.1319. Min Act: -0.0001

Data Index: 1374921 (Python Code)

Max Activating Token Index: 566

Text #5

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.1035. Min Act: -0.0002

Data Index: 1470110 (Python Code)

Max Activating Token Index: 430

Text #6

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0323. Min Act: -0.0001

Data Index: 1625419 (Python Code)

Max Activating Token Index: 754

Text #7

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.9966. Min Act: -0.0001

Data Index: 1594334 (Python Code)

Max Activating Token Index: 490

Text #8

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0021. Min Act: -0.0001

Data Index: 1519562 (Python Code)

Max Activating Token Index: 243

Text #9

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.9995. Min Act: -0.0001

Data Index: 1452417 (Python Code)

Max Activating Token Index: 727

Text #10

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.9817. Min Act: -0.0001

Data Index: 1615122 (Python Code)

Max Activating Token Index: 513

Text #11

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.9634. Min Act: -0.0002

Data Index: 1568773 (Python Code)

Max Activating Token Index: 624

Text #12

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.9129. Min Act: -0.0002

Data Index: 1538635 (Python Code)

Max Activating Token Index: 318

Text #13

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.9056. Min Act: -0.0002

Data Index: 1555327 (Python Code)

Max Activating Token Index: 205

Text #14

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.8910. Min Act: -0.0002

Data Index: 1610307 (Python Code)

Max Activating Token Index: 985

Text #15

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.8765. Min Act: -0.0001

Data Index: 1528430 (Python Code)

Max Activating Token Index: 52

Text #16

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.8563. Min Act: -0.0002

Data Index: 1423147 (Python Code)

Max Activating Token Index: 270

Text #17

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.8683. Min Act: -0.0001

Data Index: 1373374 (Python Code)

Max Activating Token Index: 460

Text #18

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.8536. Min Act: -0.0002

Data Index: 1554887 (Python Code)

Max Activating Token Index: 736

Text #19

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.8204. Min Act: -0.0001

Data Index: 1470076 (Python Code)

Max Activating Token Index: 798