Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3263 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.3982. Min Act: -0.1700
Data Index: 3028052 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.2732. Min Act: -0.1700
Data Index: 1167150 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.2732. Min Act: -0.1700
Data Index: 6479540 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.2420. Min Act: -0.1700
Data Index: 3496843 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.2420. Min Act: -0.1700
Data Index: 1814782 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.2107. Min Act: -0.1700
Data Index: 7703577 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.2107. Min Act: -0.1700
Data Index: 3750319 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.2107. Min Act: -0.1700
Data Index: 7511251 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.1795. Min Act: -0.1700
Data Index: 1153289 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.1795. Min Act: -0.1700
Data Index: 7619647 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.1795. Min Act: -0.1698
Data Index: 832802 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.1795. Min Act: -0.1700
Data Index: 7160596 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.2107. Min Act: -0.1700
Data Index: 5634386 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.1795. Min Act: -0.1699
Data Index: 2769731 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.1482. Min Act: -0.1700
Data Index: 2930137 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.1482. Min Act: -0.1700
Data Index: 1586061 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.1482. Min Act: -0.1700
Data Index: 1258070 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.1482. Min Act: -0.1700
Data Index: 2219466 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.1482. Min Act: -0.1700
Data Index: 3769325 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.1482. Min Act: -0.1699
Data Index: 3098504 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19