Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 69 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 5.0911. Min Range: -5.0911

Max Act: 5.0401. Min Act: -0.1700

Data Index: 454023 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 5.0911. Min Range: -5.0911

Max Act: 5.0262. Min Act: -0.1700

Data Index: 731611 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 5.0911. Min Range: -5.0911

Max Act: 5.0367. Min Act: -0.1700

Data Index: 1500706 (Python Code)

Max Activating Token Index: 21

Text #3

Max Range: 5.0911. Min Range: -5.0911

Max Act: 5.0825. Min Act: -0.1700

Data Index: 1644275 (Python Code)

Max Activating Token Index: 908

Text #4

Max Range: 5.0911. Min Range: -5.0911

Max Act: 5.0911. Min Act: -0.1700

Data Index: 794236 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 5.0911. Min Range: -5.0911

Max Act: 5.0274. Min Act: -0.1700

Data Index: 1329370 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 5.0911. Min Range: -5.0911

Max Act: 5.0120. Min Act: -0.1700

Data Index: 1548269 (Python Code)

Max Activating Token Index: 281

Text #7

Max Range: 5.0911. Min Range: -5.0911

Max Act: 5.0295. Min Act: -0.1700

Data Index: 1503779 (Python Code)

Max Activating Token Index: 720

Text #8

Max Range: 5.0911. Min Range: -5.0911

Max Act: 5.0357. Min Act: -0.1700

Data Index: 1618632 (Python Code)

Max Activating Token Index: 99

Text #9

Max Range: 5.0911. Min Range: -5.0911

Max Act: 4.9894. Min Act: -0.1700

Data Index: 642431 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 5.0911. Min Range: -5.0911

Max Act: 4.9802. Min Act: -0.1700

Data Index: 1552570 (Python Code)

Max Activating Token Index: 260

Text #11

Max Range: 5.0911. Min Range: -5.0911

Max Act: 5.0088. Min Act: -0.1700

Data Index: 1467706 (Python Code)

Max Activating Token Index: 174

Text #12

Max Range: 5.0911. Min Range: -5.0911

Max Act: 5.0064. Min Act: -0.1700

Data Index: 1557649 (Python Code)

Max Activating Token Index: 59

Text #13

Max Range: 5.0911. Min Range: -5.0911

Max Act: 5.0218. Min Act: -0.1700

Data Index: 1369203 (Python Code)

Max Activating Token Index: 268

Text #14

Max Range: 5.0911. Min Range: -5.0911

Max Act: 4.9985. Min Act: -0.1700

Data Index: 1429466 (Python Code)

Max Activating Token Index: 214

Text #15

Max Range: 5.0911. Min Range: -5.0911

Max Act: 4.9925. Min Act: -0.1700

Data Index: 1413927 (Python Code)

Max Activating Token Index: 21

Text #16

Max Range: 5.0911. Min Range: -5.0911

Max Act: 4.9839. Min Act: -0.1700

Data Index: 1492232 (Python Code)

Max Activating Token Index: 505

Text #17

Max Range: 5.0911. Min Range: -5.0911

Max Act: 4.9798. Min Act: -0.1700

Data Index: 1483898 (Python Code)

Max Activating Token Index: 21

Text #18

Max Range: 5.0911. Min Range: -5.0911

Max Act: 5.0238. Min Act: -0.1700

Data Index: 1479343 (Python Code)

Max Activating Token Index: 976

Text #19

Max Range: 5.0911. Min Range: -5.0911

Max Act: 4.9770. Min Act: -0.1700

Data Index: 1605934 (Python Code)

Max Activating Token Index: 29