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

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

Neuron 2828 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: 0.9611. Min Range: -0.9611

Max Act: 0.9413. Min Act: -0.0002

Data Index: 1399969 (Python Code)

Max Activating Token Index: 42

Text #1

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.9611. Min Act: -0.0002

Data Index: 1559399 (Python Code)

Max Activating Token Index: 249

Text #2

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.9215. Min Act: -0.0002

Data Index: 1504034 (Python Code)

Max Activating Token Index: 535

Text #3

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.9056. Min Act: -0.0002

Data Index: 1490591 (Python Code)

Max Activating Token Index: 281

Text #4

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8928. Min Act: -0.0002

Data Index: 1397182 (Python Code)

Max Activating Token Index: 174

Text #5

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8950. Min Act: -0.0002

Data Index: 1519261 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8782. Min Act: -0.0002

Data Index: 1493515 (Python Code)

Max Activating Token Index: 352

Text #7

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8505. Min Act: -0.0002

Data Index: 1485505 (Python Code)

Max Activating Token Index: 437

Text #8

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8424. Min Act: -0.0002

Data Index: 1488819 (Python Code)

Max Activating Token Index: 852

Text #9

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8267. Min Act: -0.0002

Data Index: 1576402 (Python Code)

Max Activating Token Index: 451

Text #10

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8324. Min Act: -0.0002

Data Index: 1465842 (Python Code)

Max Activating Token Index: 447

Text #11

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8048. Min Act: -0.0002

Data Index: 1466363 (Python Code)

Max Activating Token Index: 146

Text #12

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8182. Min Act: -0.0002

Data Index: 1615696 (Python Code)

Max Activating Token Index: 833

Text #13

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8165. Min Act: -0.0002

Data Index: 1635711 (Python Code)

Max Activating Token Index: 210

Text #14

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8110. Min Act: -0.0002

Data Index: 1583007 (Python Code)

Max Activating Token Index: 505

Text #15

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7884. Min Act: -0.0002

Data Index: 1628457 (Python Code)

Max Activating Token Index: 219

Text #16

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7911. Min Act: -0.0002

Data Index: 1555756 (Python Code)

Max Activating Token Index: 439

Text #17

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8078. Min Act: -0.0002

Data Index: 1467795 (Python Code)

Max Activating Token Index: 261

Text #18

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7978. Min Act: -0.0002

Data Index: 1593812 (Python Code)

Max Activating Token Index: 196

Text #19

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7913. Min Act: -0.0002

Data Index: 1366055 (Python Code)

Max Activating Token Index: 252