Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5822 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.7400. Min Act: -0.1700
Data Index: 3901426 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.7400. Min Act: -0.1700
Data Index: 3775115 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.6463. Min Act: -0.1700
Data Index: 5382764 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.6463. Min Act: -0.1700
Data Index: 7027576 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.6463. Min Act: -0.1700
Data Index: 3719316 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.6150. Min Act: -0.1700
Data Index: 4493949 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.5838. Min Act: -0.1700
Data Index: 3775116 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.5525. Min Act: -0.1700
Data Index: 3629606 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.5838. Min Act: -0.1700
Data Index: 764597 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.5525. Min Act: -0.1700
Data Index: 2832009 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.5525. Min Act: -0.1700
Data Index: 4206228 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.5525. Min Act: -0.1700
Data Index: 1732229 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.5525. Min Act: -0.1700
Data Index: 941612 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.5213. Min Act: -0.1700
Data Index: 4087797 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.5213. Min Act: -0.1700
Data Index: 5225144 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.5213. Min Act: -0.1700
Data Index: 640357 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.5213. Min Act: -0.1700
Data Index: 2965264 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.5525. Min Act: -0.1700
Data Index: 1556116 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.5213. Min Act: -0.1700
Data Index: 1084615 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7400. Min Range: -4.7400
Max Act: 4.5213. Min Act: -0.1700
Data Index: 5507042 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19