Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3219 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6137. Min Range: -6.6137
Max Act: 6.6137. Min Act: -0.1700
Data Index: 6530644 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6137. Min Range: -6.6137
Max Act: 6.3637. Min Act: -0.1700
Data Index: 7895276 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6137. Min Range: -6.6137
Max Act: 5.9887. Min Act: -0.1700
Data Index: 367094 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6137. Min Range: -6.6137
Max Act: 5.9887. Min Act: -0.1700
Data Index: 1122481 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6137. Min Range: -6.6137
Max Act: 5.9262. Min Act: -0.1700
Data Index: 3683769 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6137. Min Range: -6.6137
Max Act: 5.8637. Min Act: -0.1700
Data Index: 28658 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6137. Min Range: -6.6137
Max Act: 5.8637. Min Act: -0.1700
Data Index: 7280886 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6137. Min Range: -6.6137
Max Act: 5.8012. Min Act: -0.1700
Data Index: 1304983 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6137. Min Range: -6.6137
Max Act: 5.8012. Min Act: -0.1700
Data Index: 6237939 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6137. Min Range: -6.6137
Max Act: 5.7699. Min Act: -0.1700
Data Index: 4125317 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6137. Min Range: -6.6137
Max Act: 5.7699. Min Act: -0.1700
Data Index: 152314 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6137. Min Range: -6.6137
Max Act: 5.7699. Min Act: -0.1700
Data Index: 7171112 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6137. Min Range: -6.6137
Max Act: 5.7387. Min Act: -0.1700
Data Index: 7595152 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6137. Min Range: -6.6137
Max Act: 5.7387. Min Act: -0.1700
Data Index: 2174145 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6137. Min Range: -6.6137
Max Act: 5.6762. Min Act: -0.1700
Data Index: 5235594 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6137. Min Range: -6.6137
Max Act: 5.7074. Min Act: -0.1700
Data Index: 8411653 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6137. Min Range: -6.6137
Max Act: 5.6762. Min Act: -0.1700
Data Index: 7506018 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6137. Min Range: -6.6137
Max Act: 5.6762. Min Act: -0.1700
Data Index: 3215894 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6137. Min Range: -6.6137
Max Act: 5.6762. Min Act: -0.1700
Data Index: 592182 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6137. Min Range: -6.6137
Max Act: 5.6762. Min Act: -0.1700
Data Index: 5138997 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19