Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4222 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0523. Min Range: -8.0523
Max Act: 8.0523. Min Act: -0.1700
Data Index: 3819453 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.9898. Min Act: -0.1700
Data Index: 7099310 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.8648. Min Act: -0.1700
Data Index: 3520899 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.9273. Min Act: -0.1700
Data Index: 955546 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.8648. Min Act: -0.1700
Data Index: 5185214 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.8023. Min Act: -0.1700
Data Index: 7750054 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.7398. Min Act: -0.1700
Data Index: 2011390 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.6773. Min Act: -0.1700
Data Index: 5213764 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.6773. Min Act: -0.1700
Data Index: 3365213 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.6773. Min Act: -0.1700
Data Index: 8510080 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.6460. Min Act: -0.1700
Data Index: 735400 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.5835. Min Act: -0.1700
Data Index: 4144590 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.5835. Min Act: -0.1700
Data Index: 5617831 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.5835. Min Act: -0.1700
Data Index: 7914478 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.5523. Min Act: -0.1700
Data Index: 8540084 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.5210. Min Act: -0.1700
Data Index: 2216914 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.4898. Min Act: -0.1700
Data Index: 1966872 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.5210. Min Act: -0.1700
Data Index: 6880719 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.4898. Min Act: -0.1700
Data Index: 2464152 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0523. Min Range: -8.0523
Max Act: 7.4898. Min Act: -0.1700
Data Index: 2632831 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19