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

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

Neuron 2184 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: 0.9187. Min Range: -0.9187

Max Act: 0.9187. Min Act: -0.0001

Data Index: 1387038 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.8399. Min Act: -0.0002

Data Index: 1460576 (Python Code)

Max Activating Token Index: 134

Text #2

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.8114. Min Act: -0.0001

Data Index: 1402653 (Python Code)

Max Activating Token Index: 258

Text #3

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.8082. Min Act: -0.0001

Data Index: 1381942 (Python Code)

Max Activating Token Index: 120

Text #4

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7902. Min Act: -0.0001

Data Index: 1475857 (Python Code)

Max Activating Token Index: 248

Text #5

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7943. Min Act: -0.0001

Data Index: 1503406 (Python Code)

Max Activating Token Index: 357

Text #6

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7965. Min Act: -0.0001

Data Index: 1655360 (Python Code)

Max Activating Token Index: 643

Text #7

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7939. Min Act: -0.0001

Data Index: 1395463 (Python Code)

Max Activating Token Index: 17

Text #8

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7865. Min Act: -0.0002

Data Index: 1535688 (Python Code)

Max Activating Token Index: 460

Text #9

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7848. Min Act: -0.0001

Data Index: 1367744 (Python Code)

Max Activating Token Index: 936

Text #10

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7874. Min Act: -0.0001

Data Index: 1479336 (Python Code)

Max Activating Token Index: 326

Text #11

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.8021. Min Act: -0.0001

Data Index: 1531748 (Python Code)

Max Activating Token Index: 921

Text #12

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7978. Min Act: -0.0001

Data Index: 1550166 (Python Code)

Max Activating Token Index: 100

Text #13

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7903. Min Act: -0.0001

Data Index: 1614279 (Python Code)

Max Activating Token Index: 951

Text #14

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7856. Min Act: -0.0001

Data Index: 1614500 (Python Code)

Max Activating Token Index: 264

Text #15

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7823. Min Act: -0.0001

Data Index: 1456341 (Python Code)

Max Activating Token Index: 282

Text #16

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7966. Min Act: -0.0001

Data Index: 1392140 (Python Code)

Max Activating Token Index: 785

Text #17

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7770. Min Act: -0.0001

Data Index: 1452022 (Python Code)

Max Activating Token Index: 259

Text #18

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7766. Min Act: -0.0001

Data Index: 1441247 (Python Code)

Max Activating Token Index: 773

Text #19

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7651. Min Act: -0.0001

Data Index: 1652442 (Python Code)

Max Activating Token Index: 161