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

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

Neuron 853 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: 4.2443. Min Range: -4.2443

Max Act: 4.2443. Min Act: -0.1700

Data Index: 1470108 (Python Code)

Max Activating Token Index: 539

Text #1

Max Range: 4.2443. Min Range: -4.2443

Max Act: 4.0741. Min Act: -0.1699

Data Index: 1510379 (Python Code)

Max Activating Token Index: 998

Text #2

Max Range: 4.2443. Min Range: -4.2443

Max Act: 4.0526. Min Act: -0.1622

Data Index: 1374857 (Python Code)

Max Activating Token Index: 615

Text #3

Max Range: 4.2443. Min Range: -4.2443

Max Act: 3.9960. Min Act: -0.1632

Data Index: 947038 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 4.2443. Min Range: -4.2443

Max Act: 3.9675. Min Act: -0.1700

Data Index: 1556448 (Python Code)

Max Activating Token Index: 564

Text #5

Max Range: 4.2443. Min Range: -4.2443

Max Act: 3.9413. Min Act: -0.1699

Data Index: 87096 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 4.2443. Min Range: -4.2443

Max Act: 3.9212. Min Act: -0.1679

Data Index: 1384365 (Python Code)

Max Activating Token Index: 593

Text #7

Max Range: 4.2443. Min Range: -4.2443

Max Act: 3.9222. Min Act: -0.1644

Data Index: 1486772 (Python Code)

Max Activating Token Index: 270

Text #8

Max Range: 4.2443. Min Range: -4.2443

Max Act: 3.8818. Min Act: -0.1700

Data Index: 161010 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 4.2443. Min Range: -4.2443

Max Act: 3.8668. Min Act: -0.1653

Data Index: 1537273 (Python Code)

Max Activating Token Index: 696

Text #10

Max Range: 4.2443. Min Range: -4.2443

Max Act: 3.8376. Min Act: -0.1699

Data Index: 1591100 (Python Code)

Max Activating Token Index: 857

Text #11

Max Range: 4.2443. Min Range: -4.2443

Max Act: 3.8561. Min Act: -0.1700

Data Index: 1372631 (Python Code)

Max Activating Token Index: 271

Text #12

Max Range: 4.2443. Min Range: -4.2443

Max Act: 3.8327. Min Act: -0.1700

Data Index: 1645183 (Python Code)

Max Activating Token Index: 624

Text #13

Max Range: 4.2443. Min Range: -4.2443

Max Act: 3.8152. Min Act: -0.1695

Data Index: 1448604 (Python Code)

Max Activating Token Index: 800

Text #14

Max Range: 4.2443. Min Range: -4.2443

Max Act: 3.8128. Min Act: -0.1700

Data Index: 1131977 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 4.2443. Min Range: -4.2443

Max Act: 3.7990. Min Act: -0.1699

Data Index: 1392003 (Python Code)

Max Activating Token Index: 784

Text #16

Max Range: 4.2443. Min Range: -4.2443

Max Act: 3.8066. Min Act: -0.1699

Data Index: 1417267 (Python Code)

Max Activating Token Index: 571

Text #17

Max Range: 4.2443. Min Range: -4.2443

Max Act: 3.8102. Min Act: -0.1698

Data Index: 1365509 (Python Code)

Max Activating Token Index: 641

Text #18

Max Range: 4.2443. Min Range: -4.2443

Max Act: 3.8299. Min Act: -0.1695

Data Index: 1500023 (Python Code)

Max Activating Token Index: 703

Text #19

Max Range: 4.2443. Min Range: -4.2443

Max Act: 3.8116. Min Act: -0.1700

Data Index: 1581749 (Python Code)

Max Activating Token Index: 500