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

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

Neuron 1375 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: 4.1313. Min Range: -4.1313

Max Act: 4.1313. Min Act: -0.1700

Data Index: 1365727 (Python Code)

Max Activating Token Index: 783

Text #1

Max Range: 4.1313. Min Range: -4.1313

Max Act: 4.1086. Min Act: -0.1691

Data Index: 1496187 (Python Code)

Max Activating Token Index: 830

Text #2

Max Range: 4.1313. Min Range: -4.1313

Max Act: 4.0970. Min Act: -0.1700

Data Index: 1400098 (Python Code)

Max Activating Token Index: 364

Text #3

Max Range: 4.1313. Min Range: -4.1313

Max Act: 4.1056. Min Act: -0.1608

Data Index: 1565672 (Python Code)

Max Activating Token Index: 976

Text #4

Max Range: 4.1313. Min Range: -4.1313

Max Act: 4.0913. Min Act: -0.1697

Data Index: 1512605 (Python Code)

Max Activating Token Index: 655

Text #5

Max Range: 4.1313. Min Range: -4.1313

Max Act: 4.1148. Min Act: -0.1611

Data Index: 1419590 (Python Code)

Max Activating Token Index: 643

Text #6

Max Range: 4.1313. Min Range: -4.1313

Max Act: 4.0615. Min Act: -0.1688

Data Index: 1448283 (Python Code)

Max Activating Token Index: 538

Text #7

Max Range: 4.1313. Min Range: -4.1313

Max Act: 4.0835. Min Act: -0.1646

Data Index: 1433874 (Python Code)

Max Activating Token Index: 262

Text #8

Max Range: 4.1313. Min Range: -4.1313

Max Act: 4.0621. Min Act: -0.1700

Data Index: 1488549 (Python Code)

Max Activating Token Index: 935

Text #9

Max Range: 4.1313. Min Range: -4.1313

Max Act: 4.0705. Min Act: -0.1514

Data Index: 1644393 (Python Code)

Max Activating Token Index: 128

Text #10

Max Range: 4.1313. Min Range: -4.1313

Max Act: 4.0561. Min Act: -0.1660

Data Index: 1446829 (Python Code)

Max Activating Token Index: 558

Text #11

Max Range: 4.1313. Min Range: -4.1313

Max Act: 4.0541. Min Act: -0.1550

Data Index: 1647515 (Python Code)

Max Activating Token Index: 748

Text #12

Max Range: 4.1313. Min Range: -4.1313

Max Act: 4.0167. Min Act: -0.1699

Data Index: 1558793 (Python Code)

Max Activating Token Index: 1009

Text #13

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.9251. Min Act: -0.1700

Data Index: 1612342 (Python Code)

Max Activating Token Index: 888

Text #14

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.8868. Min Act: -0.1700

Data Index: 1481585 (Python Code)

Max Activating Token Index: 87

Text #15

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.8461. Min Act: -0.1602

Data Index: 1628948 (Python Code)

Max Activating Token Index: 719

Text #16

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.8526. Min Act: -0.1700

Data Index: 1367023 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.8389. Min Act: -0.1698

Data Index: 71287 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.8080. Min Act: -0.1700

Data Index: 1388595 (Python Code)

Max Activating Token Index: 250

Text #19

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.8293. Min Act: -0.1700

Data Index: 1475893 (Python Code)

Max Activating Token Index: 160