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

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

Neuron 1470 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: 4.2449. Min Range: -4.2449

Max Act: 4.2449. Min Act: -0.1698

Data Index: 1422664 (Python Code)

Max Activating Token Index: 778

Text #1

Max Range: 4.2449. Min Range: -4.2449

Max Act: 4.2066. Min Act: -0.1694

Data Index: 1505563 (Python Code)

Max Activating Token Index: 109

Text #2

Max Range: 4.2449. Min Range: -4.2449

Max Act: 4.1584. Min Act: -0.1683

Data Index: 1648165 (Python Code)

Max Activating Token Index: 900

Text #3

Max Range: 4.2449. Min Range: -4.2449

Max Act: 4.0775. Min Act: -0.1699

Data Index: 1413544 (Python Code)

Max Activating Token Index: 981

Text #4

Max Range: 4.2449. Min Range: -4.2449

Max Act: 4.1143. Min Act: -0.1696

Data Index: 1587223 (Python Code)

Max Activating Token Index: 409

Text #5

Max Range: 4.2449. Min Range: -4.2449

Max Act: 4.0834. Min Act: -0.1685

Data Index: 1648513 (Python Code)

Max Activating Token Index: 115

Text #6

Max Range: 4.2449. Min Range: -4.2449

Max Act: 4.0826. Min Act: -0.1687

Data Index: 1449426 (Python Code)

Max Activating Token Index: 528

Text #7

Max Range: 4.2449. Min Range: -4.2449

Max Act: 4.0096. Min Act: -0.1664

Data Index: 1576403 (Python Code)

Max Activating Token Index: 215

Text #8

Max Range: 4.2449. Min Range: -4.2449

Max Act: 3.9509. Min Act: -0.1699

Data Index: 1593804 (Python Code)

Max Activating Token Index: 1019

Text #9

Max Range: 4.2449. Min Range: -4.2449

Max Act: 3.9468. Min Act: -0.1630

Data Index: 1554174 (Python Code)

Max Activating Token Index: 69

Text #10

Max Range: 4.2449. Min Range: -4.2449

Max Act: 3.9099. Min Act: -0.1698

Data Index: 1615955 (Python Code)

Max Activating Token Index: 715

Text #11

Max Range: 4.2449. Min Range: -4.2449

Max Act: 3.9137. Min Act: -0.1699

Data Index: 1503953 (Python Code)

Max Activating Token Index: 468

Text #12

Max Range: 4.2449. Min Range: -4.2449

Max Act: 3.8921. Min Act: -0.1700

Data Index: 1622053 (Python Code)

Max Activating Token Index: 158

Text #13

Max Range: 4.2449. Min Range: -4.2449

Max Act: 3.8861. Min Act: -0.1543

Data Index: 1486625 (Python Code)

Max Activating Token Index: 944

Text #14

Max Range: 4.2449. Min Range: -4.2449

Max Act: 3.8486. Min Act: -0.1700

Data Index: 1420226 (Python Code)

Max Activating Token Index: 101

Text #15

Max Range: 4.2449. Min Range: -4.2449

Max Act: 3.8569. Min Act: -0.1698

Data Index: 1543457 (Python Code)

Max Activating Token Index: 258

Text #16

Max Range: 4.2449. Min Range: -4.2449

Max Act: 3.8561. Min Act: -0.1700

Data Index: 1398037 (Python Code)

Max Activating Token Index: 314

Text #17

Max Range: 4.2449. Min Range: -4.2449

Max Act: 3.8438. Min Act: -0.1700

Data Index: 1475731 (Python Code)

Max Activating Token Index: 202

Text #18

Max Range: 4.2449. Min Range: -4.2449

Max Act: 3.8453. Min Act: -0.1543

Data Index: 1544253 (Python Code)

Max Activating Token Index: 241

Text #19

Max Range: 4.2449. Min Range: -4.2449

Max Act: 3.8024. Min Act: -0.1697

Data Index: 1466507 (Python Code)

Max Activating Token Index: 1017