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

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

Neuron 712 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: 3.7895. Min Range: -3.7895

Max Act: 3.7895. Min Act: -0.1682

Data Index: 1458809 (Python Code)

Max Activating Token Index: 995

Text #1

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.7140. Min Act: -0.1700

Data Index: 1585723 (Python Code)

Max Activating Token Index: 542

Text #2

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.7260. Min Act: -0.1635

Data Index: 1388344 (Python Code)

Max Activating Token Index: 458

Text #3

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6975. Min Act: -0.1344

Data Index: 1542539 (Python Code)

Max Activating Token Index: 305

Text #4

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.7024. Min Act: -0.1663

Data Index: 1488628 (Python Code)

Max Activating Token Index: 334

Text #5

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6735. Min Act: -0.1700

Data Index: 1461265 (Python Code)

Max Activating Token Index: 763

Text #6

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6787. Min Act: -0.1344

Data Index: 1476172 (Python Code)

Max Activating Token Index: 814

Text #7

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6372. Min Act: -0.1344

Data Index: 1395566 (Python Code)

Max Activating Token Index: 245

Text #8

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6142. Min Act: -0.1698

Data Index: 1642321 (Python Code)

Max Activating Token Index: 593

Text #9

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6475. Min Act: -0.1700

Data Index: 1578280 (Python Code)

Max Activating Token Index: 1013

Text #10

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6026. Min Act: -0.1696

Data Index: 1531798 (Python Code)

Max Activating Token Index: 494

Text #11

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6103. Min Act: -0.1700

Data Index: 1368456 (Python Code)

Max Activating Token Index: 284

Text #12

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6209. Min Act: -0.1681

Data Index: 1549781 (Python Code)

Max Activating Token Index: 491

Text #13

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6142. Min Act: -0.1632

Data Index: 1361619 (Python Code)

Max Activating Token Index: 86

Text #14

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.5757. Min Act: -0.1344

Data Index: 1409024 (Python Code)

Max Activating Token Index: 509

Text #15

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.5879. Min Act: -0.1700

Data Index: 1414388 (Python Code)

Max Activating Token Index: 312

Text #16

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.5811. Min Act: -0.1692

Data Index: 1551523 (Python Code)

Max Activating Token Index: 740

Text #17

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.5653. Min Act: -0.1688

Data Index: 1372070 (Python Code)

Max Activating Token Index: 795

Text #18

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.5647. Min Act: -0.1344

Data Index: 1498524 (Python Code)

Max Activating Token Index: 555

Text #19

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.5796. Min Act: -0.1700

Data Index: 1533367 (Python Code)

Max Activating Token Index: 67