Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3736 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5731. Min Act: -0.1700
Data Index: 6017308 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5731. Min Act: -0.1700
Data Index: 432143 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5731. Min Act: -0.1700
Data Index: 8117805 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5418. Min Act: -0.1700
Data Index: 358589 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5418. Min Act: -0.1700
Data Index: 2381025 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5418. Min Act: -0.1700
Data Index: 1822435 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5418. Min Act: -0.1700
Data Index: 5923872 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5418. Min Act: -0.1700
Data Index: 8574287 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5418. Min Act: -0.1700
Data Index: 8249642 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5418. Min Act: -0.1700
Data Index: 3378323 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5418. Min Act: -0.1700
Data Index: 7393360 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5418. Min Act: -0.1700
Data Index: 2493167 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5418. Min Act: -0.1700
Data Index: 1514545 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5105. Min Act: -0.1700
Data Index: 1575889 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5105. Min Act: -0.1700
Data Index: 3501175 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5105. Min Act: -0.1700
Data Index: 4050236 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5105. Min Act: -0.1700
Data Index: 4982857 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5105. Min Act: -0.1700
Data Index: 2240967 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5105. Min Act: -0.1700
Data Index: 5004794 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5731. Min Range: -3.5731
Max Act: 3.5105. Min Act: -0.1700
Data Index: 526029 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19