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

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

Neuron 580 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: 5.2679. Min Range: -5.2679

Max Act: 5.2679. Min Act: -0.1700

Data Index: 1582463 (Python Code)

Max Activating Token Index: 823

Text #1

Max Range: 5.2679. Min Range: -5.2679

Max Act: 5.2569. Min Act: -0.1700

Data Index: 1548998 (Python Code)

Max Activating Token Index: 322

Text #2

Max Range: 5.2679. Min Range: -5.2679

Max Act: 5.2404. Min Act: -0.1700

Data Index: 1576275 (Python Code)

Max Activating Token Index: 485

Text #3

Max Range: 5.2679. Min Range: -5.2679

Max Act: 5.0784. Min Act: -0.1700

Data Index: 1379674 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 5.2679. Min Range: -5.2679

Max Act: 5.0937. Min Act: -0.1700

Data Index: 1511115 (Python Code)

Max Activating Token Index: 170

Text #5

Max Range: 5.2679. Min Range: -5.2679

Max Act: 5.0228. Min Act: -0.1700

Data Index: 1622780 (Python Code)

Max Activating Token Index: 427

Text #6

Max Range: 5.2679. Min Range: -5.2679

Max Act: 5.0091. Min Act: -0.1700

Data Index: 1459112 (Python Code)

Max Activating Token Index: 836

Text #7

Max Range: 5.2679. Min Range: -5.2679

Max Act: 5.0323. Min Act: -0.1700

Data Index: 1368118 (Python Code)

Max Activating Token Index: 336

Text #8

Max Range: 5.2679. Min Range: -5.2679

Max Act: 5.0468. Min Act: -0.1700

Data Index: 1517357 (Python Code)

Max Activating Token Index: 747

Text #9

Max Range: 5.2679. Min Range: -5.2679

Max Act: 4.9467. Min Act: -0.1700

Data Index: 1560827 (Python Code)

Max Activating Token Index: 641

Text #10

Max Range: 5.2679. Min Range: -5.2679

Max Act: 5.0193. Min Act: -0.1700

Data Index: 1598883 (Python Code)

Max Activating Token Index: 204

Text #11

Max Range: 5.2679. Min Range: -5.2679

Max Act: 4.9705. Min Act: -0.1700

Data Index: 1116155 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 5.2679. Min Range: -5.2679

Max Act: 4.9402. Min Act: -0.1700

Data Index: 775181 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 5.2679. Min Range: -5.2679

Max Act: 4.9390. Min Act: -0.1700

Data Index: 1523253 (Python Code)

Max Activating Token Index: 423

Text #14

Max Range: 5.2679. Min Range: -5.2679

Max Act: 4.9261. Min Act: -0.1700

Data Index: 1360313 (Python Code)

Max Activating Token Index: 851

Text #15

Max Range: 5.2679. Min Range: -5.2679

Max Act: 4.9334. Min Act: -0.1700

Data Index: 1593484 (Python Code)

Max Activating Token Index: 929

Text #16

Max Range: 5.2679. Min Range: -5.2679

Max Act: 4.9359. Min Act: -0.1700

Data Index: 1650642 (Python Code)

Max Activating Token Index: 889

Text #17

Max Range: 5.2679. Min Range: -5.2679

Max Act: 4.9505. Min Act: -0.1700

Data Index: 1638297 (Python Code)

Max Activating Token Index: 363

Text #18

Max Range: 5.2679. Min Range: -5.2679

Max Act: 4.9724. Min Act: -0.1700

Data Index: 1534378 (Python Code)

Max Activating Token Index: 801

Text #19

Max Range: 5.2679. Min Range: -5.2679

Max Act: 4.9366. Min Act: -0.1700

Data Index: 1452391 (Python Code)

Max Activating Token Index: 331