Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 266 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.9742. Min Act: -0.1700
Data Index: 3684335 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.9117. Min Act: -0.1700
Data Index: 6238153 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.9117. Min Act: -0.1700
Data Index: 4465269 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.8492. Min Act: -0.1700
Data Index: 1327159 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.8492. Min Act: -0.1700
Data Index: 2453578 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.8492. Min Act: -0.1700
Data Index: 8657943 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.9117. Min Act: -0.1700
Data Index: 8335880 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.7867. Min Act: -0.1700
Data Index: 5321155 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.7867. Min Act: -0.1700
Data Index: 1471023 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.7242. Min Act: -0.1700
Data Index: 1610204 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.7242. Min Act: -0.1700
Data Index: 8125503 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.7242. Min Act: -0.1700
Data Index: 4865363 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.7242. Min Act: -0.1700
Data Index: 2247436 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.5992. Min Act: -0.1700
Data Index: 4194131 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.6617. Min Act: -0.1700
Data Index: 7858114 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.5992. Min Act: -0.1700
Data Index: 7002933 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.6617. Min Act: -0.1700
Data Index: 6503584 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.6617. Min Act: -0.1700
Data Index: 4105679 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.6617. Min Act: -0.1700
Data Index: 5554503 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9742. Min Range: -8.9742
Max Act: 8.6617. Min Act: -0.1700
Data Index: 1941668 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19