Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5981 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8416. Min Range: -7.8416
Max Act: 7.8416. Min Act: -0.1700
Data Index: 4966780 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8416. Min Range: -7.8416
Max Act: 7.7479. Min Act: -0.1700
Data Index: 6651108 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8416. Min Range: -7.8416
Max Act: 7.7166. Min Act: -0.1700
Data Index: 7474999 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8416. Min Range: -7.8416
Max Act: 7.4666. Min Act: -0.1700
Data Index: 5716981 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8416. Min Range: -7.8416
Max Act: 7.3729. Min Act: -0.1700
Data Index: 7171532 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8416. Min Range: -7.8416
Max Act: 7.2479. Min Act: -0.1700
Data Index: 3825615 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8416. Min Range: -7.8416
Max Act: 7.1854. Min Act: -0.1700
Data Index: 7041957 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8416. Min Range: -7.8416
Max Act: 7.1229. Min Act: -0.1700
Data Index: 8349141 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8416. Min Range: -7.8416
Max Act: 7.0916. Min Act: -0.1700
Data Index: 6458873 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8416. Min Range: -7.8416
Max Act: 7.0604. Min Act: -0.1700
Data Index: 8286775 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8416. Min Range: -7.8416
Max Act: 7.0291. Min Act: -0.1700
Data Index: 5760515 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8416. Min Range: -7.8416
Max Act: 6.9666. Min Act: -0.1700
Data Index: 5774701 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8416. Min Range: -7.8416
Max Act: 6.9666. Min Act: -0.1700
Data Index: 6269323 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8416. Min Range: -7.8416
Max Act: 6.9666. Min Act: -0.1700
Data Index: 8570892 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8416. Min Range: -7.8416
Max Act: 6.9666. Min Act: -0.1700
Data Index: 4577419 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8416. Min Range: -7.8416
Max Act: 6.9354. Min Act: -0.1700
Data Index: 330434 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8416. Min Range: -7.8416
Max Act: 6.9354. Min Act: -0.1700
Data Index: 5189089 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8416. Min Range: -7.8416
Max Act: 6.8729. Min Act: -0.1700
Data Index: 918931 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8416. Min Range: -7.8416
Max Act: 6.8416. Min Act: -0.1700
Data Index: 1237149 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8416. Min Range: -7.8416
Max Act: 6.8416. Min Act: -0.1700
Data Index: 5460061 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19