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

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

Neuron 1775 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: 5.2135. Min Range: -5.2135

Max Act: 5.2135. Min Act: -0.1700

Data Index: 1293771 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 5.2135. Min Range: -5.2135

Max Act: 5.1812. Min Act: -0.1416

Data Index: 1594082 (Python Code)

Max Activating Token Index: 532

Text #2

Max Range: 5.2135. Min Range: -5.2135

Max Act: 5.1451. Min Act: -0.1700

Data Index: 1608961 (Python Code)

Max Activating Token Index: 165

Text #3

Max Range: 5.2135. Min Range: -5.2135

Max Act: 4.9444. Min Act: -0.1700

Data Index: 1635600 (Python Code)

Max Activating Token Index: 245

Text #4

Max Range: 5.2135. Min Range: -5.2135

Max Act: 4.9318. Min Act: -0.1699

Data Index: 1514243 (Python Code)

Max Activating Token Index: 973

Text #5

Max Range: 5.2135. Min Range: -5.2135

Max Act: 4.8906. Min Act: -0.1698

Data Index: 1453139 (Python Code)

Max Activating Token Index: 339

Text #6

Max Range: 5.2135. Min Range: -5.2135

Max Act: 4.9020. Min Act: -0.1700

Data Index: 1534530 (Python Code)

Max Activating Token Index: 889

Text #7

Max Range: 5.2135. Min Range: -5.2135

Max Act: 4.8018. Min Act: -0.1700

Data Index: 1102641 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 5.2135. Min Range: -5.2135

Max Act: 4.8163. Min Act: -0.1700

Data Index: 1573161 (Python Code)

Max Activating Token Index: 897

Text #9

Max Range: 5.2135. Min Range: -5.2135

Max Act: 4.8210. Min Act: -0.1700

Data Index: 1468181 (Python Code)

Max Activating Token Index: 515

Text #10

Max Range: 5.2135. Min Range: -5.2135

Max Act: 4.7970. Min Act: -0.1700

Data Index: 1648026 (Python Code)

Max Activating Token Index: 641

Text #11

Max Range: 5.2135. Min Range: -5.2135

Max Act: 4.7282. Min Act: -0.1671

Data Index: 1432866 (Python Code)

Max Activating Token Index: 480

Text #12

Max Range: 5.2135. Min Range: -5.2135

Max Act: 4.6845. Min Act: -0.1700

Data Index: 1605987 (Python Code)

Max Activating Token Index: 678

Text #13

Max Range: 5.2135. Min Range: -5.2135

Max Act: 4.6988. Min Act: -0.1700

Data Index: 1420709 (Python Code)

Max Activating Token Index: 973

Text #14

Max Range: 5.2135. Min Range: -5.2135

Max Act: 4.7212. Min Act: -0.1700

Data Index: 1624376 (Python Code)

Max Activating Token Index: 284

Text #15

Max Range: 5.2135. Min Range: -5.2135

Max Act: 4.6750. Min Act: -0.1700

Data Index: 1513655 (Python Code)

Max Activating Token Index: 493

Text #16

Max Range: 5.2135. Min Range: -5.2135

Max Act: 4.7014. Min Act: -0.1663

Data Index: 1578476 (Python Code)

Max Activating Token Index: 831

Text #17

Max Range: 5.2135. Min Range: -5.2135

Max Act: 4.7145. Min Act: -0.1699

Data Index: 721348 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 5.2135. Min Range: -5.2135

Max Act: 4.6474. Min Act: -0.1699

Data Index: 1432949 (Python Code)

Max Activating Token Index: 84

Text #19

Max Range: 5.2135. Min Range: -5.2135

Max Act: 4.6749. Min Act: -0.1700

Data Index: 1598976 (Python Code)

Max Activating Token Index: 37