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

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

Neuron 1886 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: 3.0021. Min Range: -3.0021

Max Act: 3.0021. Min Act: -0.1349

Data Index: 1437176 (Python Code)

Max Activating Token Index: 915

Text #1

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.9825. Min Act: -0.1253

Data Index: 1410051 (Python Code)

Max Activating Token Index: 648

Text #2

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.9867. Min Act: -0.1668

Data Index: 1537566 (Python Code)

Max Activating Token Index: 56

Text #3

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.9704. Min Act: -0.1686

Data Index: 1014764 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.9828. Min Act: -0.1680

Data Index: 1431045 (Python Code)

Max Activating Token Index: 350

Text #5

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.9604. Min Act: -0.1700

Data Index: 520647 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.9837. Min Act: -0.1700

Data Index: 831004 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.9342. Min Act: -0.1700

Data Index: 1625037 (Python Code)

Max Activating Token Index: 406

Text #8

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.9115. Min Act: -0.1700

Data Index: 1465696 (Python Code)

Max Activating Token Index: 660

Text #9

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.9158. Min Act: -0.1583

Data Index: 1485683 (Python Code)

Max Activating Token Index: 121

Text #10

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.9303. Min Act: -0.0193

Data Index: 1331970 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.9197. Min Act: -0.0878

Data Index: 103994 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.9013. Min Act: -0.1686

Data Index: 448952 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.9124. Min Act: -0.1141

Data Index: 1609478 (Python Code)

Max Activating Token Index: 937

Text #14

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.9165. Min Act: -0.1699

Data Index: 1406857 (Python Code)

Max Activating Token Index: 748

Text #15

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.8864. Min Act: -0.1207

Data Index: 1507730 (Python Code)

Max Activating Token Index: 398

Text #16

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.8986. Min Act: -0.1675

Data Index: 1427282 (Python Code)

Max Activating Token Index: 316

Text #17

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.8794. Min Act: -0.1700

Data Index: 799639 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.8770. Min Act: -0.1700

Data Index: 1444690 (Python Code)

Max Activating Token Index: 811

Text #19

Max Range: 3.0021. Min Range: -3.0021

Max Act: 2.8646. Min Act: -0.1692

Data Index: 1363996 (Python Code)

Max Activating Token Index: 997