Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3017 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1703. Min Range: -4.1703
Max Act: 4.1703. Min Act: -0.1700
Data Index: 6397900 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1703. Min Range: -4.1703
Max Act: 4.1078. Min Act: -0.1700
Data Index: 5190322 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1703. Min Range: -4.1703
Max Act: 4.0766. Min Act: -0.1700
Data Index: 3918145 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1703. Min Range: -4.1703
Max Act: 4.0766. Min Act: -0.1700
Data Index: 6536066 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1703. Min Range: -4.1703
Max Act: 4.0453. Min Act: -0.1700
Data Index: 1585838 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1703. Min Range: -4.1703
Max Act: 4.0140. Min Act: -0.1700
Data Index: 222107 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1703. Min Range: -4.1703
Max Act: 4.0140. Min Act: -0.1700
Data Index: 6836517 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1703. Min Range: -4.1703
Max Act: 4.0140. Min Act: -0.1700
Data Index: 7368768 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1703. Min Range: -4.1703
Max Act: 3.9828. Min Act: -0.1700
Data Index: 7471246 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1703. Min Range: -4.1703
Max Act: 3.9828. Min Act: -0.1700
Data Index: 2382781 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1703. Min Range: -4.1703
Max Act: 3.9828. Min Act: -0.1700
Data Index: 676598 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1703. Min Range: -4.1703
Max Act: 3.9828. Min Act: -0.1700
Data Index: 2356308 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1703. Min Range: -4.1703
Max Act: 3.9828. Min Act: -0.1700
Data Index: 5568313 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1703. Min Range: -4.1703
Max Act: 3.9828. Min Act: -0.1700
Data Index: 4939096 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1703. Min Range: -4.1703
Max Act: 3.9828. Min Act: -0.1700
Data Index: 6762416 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1703. Min Range: -4.1703
Max Act: 3.9828. Min Act: -0.1700
Data Index: 4766472 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1703. Min Range: -4.1703
Max Act: 3.9828. Min Act: -0.1700
Data Index: 450116 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1703. Min Range: -4.1703
Max Act: 3.9203. Min Act: -0.1700
Data Index: 5023654 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1703. Min Range: -4.1703
Max Act: 3.9515. Min Act: -0.1700
Data Index: 630873 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1703. Min Range: -4.1703
Max Act: 3.9515. Min Act: -0.1700
Data Index: 5197585 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19