Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 400 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.3695. Min Act: -0.1700
Data Index: 1558727 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.2637. Min Act: -0.1700
Data Index: 2507005 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.2460. Min Act: -0.1700
Data Index: 5030479 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.2284. Min Act: -0.1700
Data Index: 7915162 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.2284. Min Act: -0.1700
Data Index: 3371807 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.2460. Min Act: -0.1700
Data Index: 3368951 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.2460. Min Act: -0.1700
Data Index: 4882104 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.2284. Min Act: -0.1700
Data Index: 2096472 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.2460. Min Act: -0.1700
Data Index: 8349657 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.2284. Min Act: -0.1700
Data Index: 4666875 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.2108. Min Act: -0.1700
Data Index: 3243952 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.2284. Min Act: -0.1700
Data Index: 8349674 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.2284. Min Act: -0.1700
Data Index: 8349658 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.2108. Min Act: -0.1700
Data Index: 3200492 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.2284. Min Act: -0.1700
Data Index: 3029075 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.2108. Min Act: -0.1700
Data Index: 5492448 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.1932. Min Act: -0.1700
Data Index: 1547469 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.1932. Min Act: -0.1700
Data Index: 5006261 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.1756. Min Act: -0.1700
Data Index: 4339541 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3695. Min Range: -1.3695
Max Act: 1.2108. Min Act: -0.1700
Data Index: 191290 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19