Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2240 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.6274. Min Act: -0.1700
Data Index: 3192177 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.6587. Min Act: -0.1700
Data Index: 4587633 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.6274. Min Act: -0.1700
Data Index: 7183179 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.5337. Min Act: -0.1700
Data Index: 2524685 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.5024. Min Act: -0.1700
Data Index: 6723266 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.4712. Min Act: -0.1700
Data Index: 6742816 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.4712. Min Act: -0.1700
Data Index: 4192219 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.4712. Min Act: -0.1700
Data Index: 6124929 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.4399. Min Act: -0.1700
Data Index: 1510078 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.4712. Min Act: -0.1700
Data Index: 5747462 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.4712. Min Act: -0.1700
Data Index: 6463762 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.4399. Min Act: -0.1700
Data Index: 5866896 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.4399. Min Act: -0.1700
Data Index: 4473766 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.4399. Min Act: -0.1700
Data Index: 2044726 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.4399. Min Act: -0.1700
Data Index: 243247 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.4087. Min Act: -0.1700
Data Index: 5885563 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.4087. Min Act: -0.1700
Data Index: 1172612 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.4087. Min Act: -0.1700
Data Index: 6198797 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.4087. Min Act: -0.1700
Data Index: 38740 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6587. Min Range: -4.6587
Max Act: 4.4087. Min Act: -0.1700
Data Index: 1066601 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19