Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6380 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.7016. Min Act: -0.1700
Data Index: 5631055 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.6391. Min Act: -0.1700
Data Index: 1256152 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.6391. Min Act: -0.1700
Data Index: 7174369 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.6078. Min Act: -0.1700
Data Index: 6199777 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.5766. Min Act: -0.1700
Data Index: 4971909 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.5766. Min Act: -0.1700
Data Index: 1546383 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.6078. Min Act: -0.1700
Data Index: 2287561 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.5766. Min Act: -0.1700
Data Index: 8401917 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.4828. Min Act: -0.1700
Data Index: 7248972 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.4516. Min Act: -0.1700
Data Index: 4994513 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.3891. Min Act: -0.1700
Data Index: 7060615 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.3891. Min Act: -0.1700
Data Index: 7717153 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.4203. Min Act: -0.1700
Data Index: 7324378 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.3891. Min Act: -0.1700
Data Index: 8718641 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.3891. Min Act: -0.1700
Data Index: 7873517 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.3891. Min Act: -0.1700
Data Index: 3364754 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.3578. Min Act: -0.1700
Data Index: 3010303 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.3266. Min Act: -0.1700
Data Index: 7046206 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.2953. Min Act: -0.1700
Data Index: 2288189 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7016. Min Range: -7.7016
Max Act: 7.2328. Min Act: -0.1700
Data Index: 7806793 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19