Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4972 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.5741. Min Act: -0.1700
Data Index: 1004709 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.5115. Min Act: -0.1700
Data Index: 6744714 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.5115. Min Act: -0.1700
Data Index: 6745619 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.4802. Min Act: -0.1700
Data Index: 2581871 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.4802. Min Act: -0.1700
Data Index: 8504561 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.5115. Min Act: -0.1700
Data Index: 4172819 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.4645. Min Act: -0.1700
Data Index: 306610 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.4175. Min Act: -0.1700
Data Index: 4292847 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.4018. Min Act: -0.1700
Data Index: 8115271 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.4018. Min Act: -0.1700
Data Index: 4161218 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.4018. Min Act: -0.1700
Data Index: 984759 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.3862. Min Act: -0.1700
Data Index: 5456984 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.3862. Min Act: -0.1700
Data Index: 5649075 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.3862. Min Act: -0.1700
Data Index: 3478449 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.3862. Min Act: -0.1700
Data Index: 8777304 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.3705. Min Act: -0.1700
Data Index: 8575548 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.3548. Min Act: -0.1700
Data Index: 5319927 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.3548. Min Act: -0.1700
Data Index: 5456982 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.3391. Min Act: -0.1700
Data Index: 5456986 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.3391. Min Act: -0.1700
Data Index: 4310074 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19