Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1868 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1541. Min Range: -8.1541
Max Act: 8.1541. Min Act: -0.1700
Data Index: 1008720 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1541. Min Range: -8.1541
Max Act: 8.0291. Min Act: -0.1700
Data Index: 6243534 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1541. Min Range: -8.1541
Max Act: 7.7791. Min Act: -0.1700
Data Index: 3918330 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1541. Min Range: -8.1541
Max Act: 7.7791. Min Act: -0.1700
Data Index: 4553926 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1541. Min Range: -8.1541
Max Act: 7.7166. Min Act: -0.1700
Data Index: 2483978 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1541. Min Range: -8.1541
Max Act: 7.7166. Min Act: -0.1700
Data Index: 8102612 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1541. Min Range: -8.1541
Max Act: 7.7166. Min Act: -0.1700
Data Index: 3178015 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1541. Min Range: -8.1541
Max Act: 7.7166. Min Act: -0.1700
Data Index: 6587477 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1541. Min Range: -8.1541
Max Act: 7.6541. Min Act: -0.1700
Data Index: 8811198 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1541. Min Range: -8.1541
Max Act: 7.5916. Min Act: -0.1700
Data Index: 6668943 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1541. Min Range: -8.1541
Max Act: 7.6541. Min Act: -0.1700
Data Index: 6596916 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1541. Min Range: -8.1541
Max Act: 7.6541. Min Act: -0.1700
Data Index: 4616818 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1541. Min Range: -8.1541
Max Act: 7.6541. Min Act: -0.1700
Data Index: 4885886 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1541. Min Range: -8.1541
Max Act: 7.6541. Min Act: -0.1700
Data Index: 2665609 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1541. Min Range: -8.1541
Max Act: 7.6541. Min Act: -0.1700
Data Index: 4880892 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1541. Min Range: -8.1541
Max Act: 7.5916. Min Act: -0.1700
Data Index: 5661433 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1541. Min Range: -8.1541
Max Act: 7.5916. Min Act: -0.1700
Data Index: 937709 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1541. Min Range: -8.1541
Max Act: 7.5916. Min Act: -0.1700
Data Index: 3356414 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1541. Min Range: -8.1541
Max Act: 7.5916. Min Act: -0.1700
Data Index: 3717612 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1541. Min Range: -8.1541
Max Act: 7.5916. Min Act: -0.1700
Data Index: 4452733 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19