Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 29 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 6.0854. Min Range: -6.0854
Max Act: 6.0854. Min Act: -0.1700
Data Index: 706395 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0854. Min Range: -6.0854
Max Act: 5.9916. Min Act: -0.1700
Data Index: 1591497 (Python Code)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0854. Min Range: -6.0854
Max Act: 5.9916. Min Act: -0.1700
Data Index: 1150175 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0854. Min Range: -6.0854
Max Act: 5.8666. Min Act: -0.1700
Data Index: 1459705 (Python Code)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0854. Min Range: -6.0854
Max Act: 5.8979. Min Act: -0.1700
Data Index: 1436881 (Python Code)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0854. Min Range: -6.0854
Max Act: 5.7729. Min Act: -0.1700
Data Index: 372575 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0854. Min Range: -6.0854
Max Act: 5.8041. Min Act: -0.1700
Data Index: 350770 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0854. Min Range: -6.0854
Max Act: 5.8666. Min Act: -0.1700
Data Index: 1048915 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0854. Min Range: -6.0854
Max Act: 5.7416. Min Act: -0.1700
Data Index: 303288 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0854. Min Range: -6.0854
Max Act: 5.7729. Min Act: -0.1700
Data Index: 1241560 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0854. Min Range: -6.0854
Max Act: 5.7104. Min Act: -0.1699
Data Index: 1556637 (Python Code)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0854. Min Range: -6.0854
Max Act: 5.8354. Min Act: -0.1699
Data Index: 1387006 (Python Code)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0854. Min Range: -6.0854
Max Act: 5.7416. Min Act: -0.1700
Data Index: 1420056 (Python Code)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0854. Min Range: -6.0854
Max Act: 5.8041. Min Act: -0.1699
Data Index: 1365601 (Python Code)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0854. Min Range: -6.0854
Max Act: 5.8041. Min Act: -0.1700
Data Index: 1438041 (Python Code)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0854. Min Range: -6.0854
Max Act: 5.8041. Min Act: -0.1700
Data Index: 1533659 (Python Code)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0854. Min Range: -6.0854
Max Act: 5.7729. Min Act: -0.1700
Data Index: 76261 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0854. Min Range: -6.0854
Max Act: 5.7416. Min Act: -0.1700
Data Index: 19459 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0854. Min Range: -6.0854
Max Act: 5.7416. Min Act: -0.1699
Data Index: 1426454 (Python Code)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0854. Min Range: -6.0854
Max Act: 5.7104. Min Act: -0.1695
Data Index: 1526049 (Python Code)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19