Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2159 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1229. Min Range: -8.1229
Max Act: 8.1229. Min Act: -0.1700
Data Index: 631584 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1229. Min Range: -8.1229
Max Act: 7.5291. Min Act: -0.1700
Data Index: 2371230 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1229. Min Range: -8.1229
Max Act: 7.3416. Min Act: -0.1700
Data Index: 96134 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1229. Min Range: -8.1229
Max Act: 7.2479. Min Act: -0.1700
Data Index: 925921 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1229. Min Range: -8.1229
Max Act: 7.1541. Min Act: -0.1700
Data Index: 8441895 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1229. Min Range: -8.1229
Max Act: 7.1229. Min Act: -0.1700
Data Index: 8085304 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1229. Min Range: -8.1229
Max Act: 7.1229. Min Act: -0.1700
Data Index: 5367289 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1229. Min Range: -8.1229
Max Act: 7.0916. Min Act: -0.1700
Data Index: 8561451 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1229. Min Range: -8.1229
Max Act: 7.0604. Min Act: -0.1700
Data Index: 327068 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1229. Min Range: -8.1229
Max Act: 7.0291. Min Act: -0.1700
Data Index: 7128496 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1229. Min Range: -8.1229
Max Act: 7.0291. Min Act: -0.1700
Data Index: 5434764 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1229. Min Range: -8.1229
Max Act: 6.9354. Min Act: -0.1700
Data Index: 6657593 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1229. Min Range: -8.1229
Max Act: 6.9354. Min Act: -0.1700
Data Index: 7244020 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1229. Min Range: -8.1229
Max Act: 6.9041. Min Act: -0.1700
Data Index: 7160319 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1229. Min Range: -8.1229
Max Act: 6.9041. Min Act: -0.1700
Data Index: 6713944 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1229. Min Range: -8.1229
Max Act: 6.9041. Min Act: -0.1700
Data Index: 6657594 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1229. Min Range: -8.1229
Max Act: 6.8729. Min Act: -0.1700
Data Index: 3577938 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1229. Min Range: -8.1229
Max Act: 6.8729. Min Act: -0.1700
Data Index: 6457437 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1229. Min Range: -8.1229
Max Act: 6.8729. Min Act: -0.1700
Data Index: 142773 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1229. Min Range: -8.1229
Max Act: 6.8729. Min Act: -0.1700
Data Index: 814234 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19