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

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

Neuron 679 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: 3.6225. Min Range: -3.6225

Max Act: 3.6225. Min Act: -0.1700

Data Index: 1640625 (Python Code)

Max Activating Token Index: 417

Text #1

Max Range: 3.6225. Min Range: -3.6225

Max Act: 3.6014. Min Act: -0.1699

Data Index: 1437496 (Python Code)

Max Activating Token Index: 178

Text #2

Max Range: 3.6225. Min Range: -3.6225

Max Act: 3.5921. Min Act: -0.1693

Data Index: 1404172 (Python Code)

Max Activating Token Index: 171

Text #3

Max Range: 3.6225. Min Range: -3.6225

Max Act: 3.5599. Min Act: -0.1699

Data Index: 1545753 (Python Code)

Max Activating Token Index: 747

Text #4

Max Range: 3.6225. Min Range: -3.6225

Max Act: 3.5783. Min Act: -0.1699

Data Index: 1636034 (Python Code)

Max Activating Token Index: 385

Text #5

Max Range: 3.6225. Min Range: -3.6225

Max Act: 3.5747. Min Act: -0.1700

Data Index: 1512988 (Python Code)

Max Activating Token Index: 455

Text #6

Max Range: 3.6225. Min Range: -3.6225

Max Act: 3.5213. Min Act: -0.1481

Data Index: 468578 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 3.6225. Min Range: -3.6225

Max Act: 3.5340. Min Act: -0.1481

Data Index: 1486189 (Python Code)

Max Activating Token Index: 388

Text #8

Max Range: 3.6225. Min Range: -3.6225

Max Act: 3.5005. Min Act: -0.1539

Data Index: 105264 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 3.6225. Min Range: -3.6225

Max Act: 3.5212. Min Act: -0.1620

Data Index: 1508292 (Python Code)

Max Activating Token Index: 630

Text #10

Max Range: 3.6225. Min Range: -3.6225

Max Act: 3.4509. Min Act: -0.1661

Data Index: 1431143 (Python Code)

Max Activating Token Index: 715

Text #11

Max Range: 3.6225. Min Range: -3.6225

Max Act: 3.4653. Min Act: -0.1481

Data Index: 1572491 (Python Code)

Max Activating Token Index: 414

Text #12

Max Range: 3.6225. Min Range: -3.6225

Max Act: 3.4650. Min Act: -0.1692

Data Index: 1633021 (Python Code)

Max Activating Token Index: 948

Text #13

Max Range: 3.6225. Min Range: -3.6225

Max Act: 3.4607. Min Act: -0.1697

Data Index: 484583 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 3.6225. Min Range: -3.6225

Max Act: 3.4626. Min Act: -0.1481

Data Index: 1150823 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 3.6225. Min Range: -3.6225

Max Act: 3.4688. Min Act: -0.1674

Data Index: 341971 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 3.6225. Min Range: -3.6225

Max Act: 3.4663. Min Act: -0.1700

Data Index: 1036643 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 3.6225. Min Range: -3.6225

Max Act: 3.4625. Min Act: -0.1700

Data Index: 106760 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 3.6225. Min Range: -3.6225

Max Act: 3.4697. Min Act: -0.1691

Data Index: 1291583 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 3.6225. Min Range: -3.6225

Max Act: 3.4911. Min Act: -0.1612

Data Index: 1475508 (Python Code)

Max Activating Token Index: 541