Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4309 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.9087. Min Act: -0.1700
Data Index: 7806286 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.7525. Min Act: -0.1700
Data Index: 4340234 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.6275. Min Act: -0.1700
Data Index: 4685972 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.5962. Min Act: -0.1700
Data Index: 6293316 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.5650. Min Act: -0.1700
Data Index: 2677947 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.5650. Min Act: -0.1700
Data Index: 6212882 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.5650. Min Act: -0.1700
Data Index: 5288857 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.5337. Min Act: -0.1700
Data Index: 1807090 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.5337. Min Act: -0.1700
Data Index: 5482449 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.5650. Min Act: -0.1700
Data Index: 5667736 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.5025. Min Act: -0.1700
Data Index: 6327689 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.5025. Min Act: -0.1700
Data Index: 3471523 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.5025. Min Act: -0.1700
Data Index: 3558355 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.4712. Min Act: -0.1700
Data Index: 4079345 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.4712. Min Act: -0.1700
Data Index: 2877470 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.5025. Min Act: -0.1700
Data Index: 3750849 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.4400. Min Act: -0.1700
Data Index: 3754564 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.4400. Min Act: -0.1700
Data Index: 4057440 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.4400. Min Act: -0.1700
Data Index: 3759275 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9087. Min Range: -4.9087
Max Act: 4.4087. Min Act: -0.1700
Data Index: 4140821 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19