Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2162 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.8243. Min Act: -0.1700
Data Index: 7679 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.7930. Min Act: -0.1700
Data Index: 1718678 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.7617. Min Act: -0.1700
Data Index: 4500093 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.7617. Min Act: -0.1700
Data Index: 3216116 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.7617. Min Act: -0.1700
Data Index: 2796955 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.7617. Min Act: -0.1700
Data Index: 8375101 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.7617. Min Act: -0.1700
Data Index: 6613540 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.7617. Min Act: -0.1700
Data Index: 4780812 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.7617. Min Act: -0.1700
Data Index: 4239124 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.7304. Min Act: -0.1700
Data Index: 1364806 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.7304. Min Act: -0.1700
Data Index: 1590414 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.7304. Min Act: -0.1700
Data Index: 1666256 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.7304. Min Act: -0.1700
Data Index: 2001295 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.7304. Min Act: -0.1700
Data Index: 2068227 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.7304. Min Act: -0.1700
Data Index: 2549585 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.7304. Min Act: -0.1700
Data Index: 2579851 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.7304. Min Act: -0.1700
Data Index: 312386 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.7304. Min Act: -0.1700
Data Index: 2713835 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.7304. Min Act: -0.1700
Data Index: 2983649 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8243. Min Range: -3.8243
Max Act: 3.7304. Min Act: -0.1700
Data Index: 884616 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19