Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4611 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3800. Min Range: -4.3800
Max Act: 4.3800. Min Act: -0.1700
Data Index: 1919482 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3800. Min Range: -4.3800
Max Act: 4.0987. Min Act: -0.1700
Data Index: 3865215 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3800. Min Range: -4.3800
Max Act: 4.0987. Min Act: -0.1700
Data Index: 5281708 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3800. Min Range: -4.3800
Max Act: 4.0987. Min Act: -0.1700
Data Index: 4817264 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3800. Min Range: -4.3800
Max Act: 4.0362. Min Act: -0.1700
Data Index: 5055869 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3800. Min Range: -4.3800
Max Act: 4.0674. Min Act: -0.1700
Data Index: 5405356 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3800. Min Range: -4.3800
Max Act: 4.0674. Min Act: -0.1700
Data Index: 5629294 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3800. Min Range: -4.3800
Max Act: 4.0362. Min Act: -0.1700
Data Index: 865283 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3800. Min Range: -4.3800
Max Act: 4.0362. Min Act: -0.1700
Data Index: 7799031 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3800. Min Range: -4.3800
Max Act: 4.0362. Min Act: -0.1700
Data Index: 4105071 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3800. Min Range: -4.3800
Max Act: 4.0362. Min Act: -0.1700
Data Index: 3519325 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3800. Min Range: -4.3800
Max Act: 4.0049. Min Act: -0.1700
Data Index: 6668788 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3800. Min Range: -4.3800
Max Act: 3.9736. Min Act: -0.1700
Data Index: 6881040 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3800. Min Range: -4.3800
Max Act: 3.9736. Min Act: -0.1700
Data Index: 2555613 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3800. Min Range: -4.3800
Max Act: 3.9424. Min Act: -0.1700
Data Index: 1518406 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3800. Min Range: -4.3800
Max Act: 3.9424. Min Act: -0.1700
Data Index: 3162909 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3800. Min Range: -4.3800
Max Act: 3.9736. Min Act: -0.1700
Data Index: 1165089 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3800. Min Range: -4.3800
Max Act: 3.9736. Min Act: -0.1700
Data Index: 4614938 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3800. Min Range: -4.3800
Max Act: 3.9736. Min Act: -0.1700
Data Index: 3019632 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3800. Min Range: -4.3800
Max Act: 3.9424. Min Act: -0.1700
Data Index: 5288130 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19