Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1640 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.6598. Min Act: -0.1700
Data Index: 2330774 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.5036. Min Act: -0.1700
Data Index: 1173534 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.4411. Min Act: -0.1700
Data Index: 3126615 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.3161. Min Act: -0.1700
Data Index: 2602627 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.3161. Min Act: -0.1700
Data Index: 3151096 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.2848. Min Act: -0.1700
Data Index: 1112006 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.2848. Min Act: -0.1700
Data Index: 3700366 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.2536. Min Act: -0.1700
Data Index: 7698927 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.2536. Min Act: -0.1700
Data Index: 3296383 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.2536. Min Act: -0.1700
Data Index: 2191696 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.2223. Min Act: -0.1700
Data Index: 3693215 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.2536. Min Act: -0.1700
Data Index: 5750962 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.2223. Min Act: -0.1700
Data Index: 1888861 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.2223. Min Act: -0.1700
Data Index: 7435101 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.1911. Min Act: -0.1700
Data Index: 2265867 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.1598. Min Act: -0.1700
Data Index: 100913 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.1598. Min Act: -0.1700
Data Index: 1573197 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.1286. Min Act: -0.1700
Data Index: 4556868 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.1286. Min Act: -0.1700
Data Index: 7037783 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6598. Min Range: -6.6598
Max Act: 6.1286. Min Act: -0.1700
Data Index: 7497553 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19