Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2615 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1582. Min Range: -5.1582
Max Act: 5.1582. Min Act: -0.1700
Data Index: 1980312 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1582. Min Range: -5.1582
Max Act: 5.0020. Min Act: -0.1700
Data Index: 923356 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1582. Min Range: -5.1582
Max Act: 4.9707. Min Act: -0.1700
Data Index: 2424174 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1582. Min Range: -5.1582
Max Act: 4.9395. Min Act: -0.1700
Data Index: 1254580 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1582. Min Range: -5.1582
Max Act: 4.8770. Min Act: -0.1700
Data Index: 3698888 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1582. Min Range: -5.1582
Max Act: 4.9082. Min Act: -0.1700
Data Index: 6358776 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1582. Min Range: -5.1582
Max Act: 4.8770. Min Act: -0.1700
Data Index: 4339659 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1582. Min Range: -5.1582
Max Act: 4.8770. Min Act: -0.1700
Data Index: 7707245 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1582. Min Range: -5.1582
Max Act: 4.8770. Min Act: -0.1700
Data Index: 2991264 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1582. Min Range: -5.1582
Max Act: 4.8145. Min Act: -0.1700
Data Index: 1980311 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1582. Min Range: -5.1582
Max Act: 4.8145. Min Act: -0.1700
Data Index: 3698886 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1582. Min Range: -5.1582
Max Act: 4.8145. Min Act: -0.1700
Data Index: 6358780 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1582. Min Range: -5.1582
Max Act: 4.8145. Min Act: -0.1700
Data Index: 4983371 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1582. Min Range: -5.1582
Max Act: 4.8145. Min Act: -0.1700
Data Index: 2991282 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1582. Min Range: -5.1582
Max Act: 4.8145. Min Act: -0.1700
Data Index: 5678299 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1582. Min Range: -5.1582
Max Act: 4.8145. Min Act: -0.1700
Data Index: 3962366 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1582. Min Range: -5.1582
Max Act: 4.8145. Min Act: -0.1700
Data Index: 984758 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1582. Min Range: -5.1582
Max Act: 4.7832. Min Act: -0.1700
Data Index: 5223633 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1582. Min Range: -5.1582
Max Act: 4.7832. Min Act: -0.1700
Data Index: 6225801 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1582. Min Range: -5.1582
Max Act: 4.7832. Min Act: -0.1700
Data Index: 2936569 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19