Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4993 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2336. Min Range: -5.2336
Max Act: 5.2336. Min Act: -0.1700
Data Index: 1551831 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2336. Min Range: -5.2336
Max Act: 5.1086. Min Act: -0.1700
Data Index: 8787156 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2336. Min Range: -5.2336
Max Act: 5.0461. Min Act: -0.1700
Data Index: 3526598 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2336. Min Range: -5.2336
Max Act: 4.9836. Min Act: -0.1700
Data Index: 5385404 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2336. Min Range: -5.2336
Max Act: 4.9211. Min Act: -0.1700
Data Index: 3775311 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2336. Min Range: -5.2336
Max Act: 4.8586. Min Act: -0.1700
Data Index: 2778062 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2336. Min Range: -5.2336
Max Act: 4.8274. Min Act: -0.1700
Data Index: 1014503 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2336. Min Range: -5.2336
Max Act: 4.7649. Min Act: -0.1700
Data Index: 6832969 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2336. Min Range: -5.2336
Max Act: 4.7649. Min Act: -0.1700
Data Index: 3329872 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2336. Min Range: -5.2336
Max Act: 4.7336. Min Act: -0.1700
Data Index: 6858760 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2336. Min Range: -5.2336
Max Act: 4.7649. Min Act: -0.1700
Data Index: 6362353 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2336. Min Range: -5.2336
Max Act: 4.7649. Min Act: -0.1700
Data Index: 6288773 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2336. Min Range: -5.2336
Max Act: 4.7336. Min Act: -0.1700
Data Index: 3800218 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2336. Min Range: -5.2336
Max Act: 4.7336. Min Act: -0.1700
Data Index: 5576293 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2336. Min Range: -5.2336
Max Act: 4.7024. Min Act: -0.1700
Data Index: 6858761 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2336. Min Range: -5.2336
Max Act: 4.7024. Min Act: -0.1700
Data Index: 8141632 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2336. Min Range: -5.2336
Max Act: 4.7024. Min Act: -0.1700
Data Index: 1440429 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2336. Min Range: -5.2336
Max Act: 4.7024. Min Act: -0.1700
Data Index: 260889 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2336. Min Range: -5.2336
Max Act: 4.7336. Min Act: -0.1700
Data Index: 6494873 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2336. Min Range: -5.2336
Max Act: 4.6711. Min Act: -0.1700
Data Index: 4946631 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19