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

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

Neuron 249 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: 3.8104. Min Range: -3.8104

Max Act: 3.7913. Min Act: -0.1697

Data Index: 413206 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.8104. Min Act: -0.1182

Data Index: 1188341 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.7821. Min Act: -0.1645

Data Index: 1365784 (Python Code)

Max Activating Token Index: 439

Text #3

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.7357. Min Act: -0.1700

Data Index: 1454277 (Python Code)

Max Activating Token Index: 924

Text #4

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6777. Min Act: -0.1695

Data Index: 226733 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6884. Min Act: -0.1700

Data Index: 702501 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6951. Min Act: -0.1700

Data Index: 829392 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6693. Min Act: -0.1677

Data Index: 1451237 (Python Code)

Max Activating Token Index: 870

Text #8

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6356. Min Act: -0.1700

Data Index: 1463284 (Python Code)

Max Activating Token Index: 474

Text #9

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6256. Min Act: -0.1700

Data Index: 1483261 (Python Code)

Max Activating Token Index: 643

Text #10

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.5745. Min Act: -0.1697

Data Index: 1495708 (Python Code)

Max Activating Token Index: 585

Text #11

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.5693. Min Act: -0.1700

Data Index: 1418994 (Python Code)

Max Activating Token Index: 73

Text #12

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.5994. Min Act: -0.1700

Data Index: 1257109 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.5630. Min Act: -0.1423

Data Index: 490345 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.5591. Min Act: -0.1700

Data Index: 1406617 (Python Code)

Max Activating Token Index: 725

Text #15

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.5775. Min Act: -0.1699

Data Index: 677008 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.5348. Min Act: -0.1700

Data Index: 480363 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.5230. Min Act: -0.1657

Data Index: 1088864 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.5246. Min Act: -0.1700

Data Index: 1198314 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.4769. Min Act: -0.1698

Data Index: 137353 (C4 (Web Text))

Max Activating Token Index: 116