Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3622 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.9411. Min Act: -0.1700
Data Index: 4848548 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.9411. Min Act: -0.1700
Data Index: 7904228 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.7535. Min Act: -0.1700
Data Index: 1837407 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.7222. Min Act: -0.1700
Data Index: 458591 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.6909. Min Act: -0.1700
Data Index: 6920997 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.6909. Min Act: -0.1700
Data Index: 3658307 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.6909. Min Act: -0.1700
Data Index: 8070243 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.6596. Min Act: -0.1700
Data Index: 408230 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.6596. Min Act: -0.1700
Data Index: 5706304 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.6596. Min Act: -0.1700
Data Index: 280206 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.5970. Min Act: -0.1700
Data Index: 2379551 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.5970. Min Act: -0.1700
Data Index: 1355003 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.5970. Min Act: -0.1700
Data Index: 458593 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.5970. Min Act: -0.1700
Data Index: 1826487 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.5970. Min Act: -0.1700
Data Index: 2547383 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.5657. Min Act: -0.1700
Data Index: 3331590 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.5657. Min Act: -0.1700
Data Index: 6107720 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.5657. Min Act: -0.1700
Data Index: 7298981 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.5344. Min Act: -0.1700
Data Index: 6794186 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9411. Min Range: -3.9411
Max Act: 3.5344. Min Act: -0.1700
Data Index: 617748 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19