Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5144 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.8879. Min Act: -0.1700
Data Index: 7687437 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.3879. Min Act: -0.1700
Data Index: 714518 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.3879. Min Act: -0.1700
Data Index: 5297966 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.2629. Min Act: -0.1700
Data Index: 5815919 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.2629. Min Act: -0.1700
Data Index: 7662794 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.2629. Min Act: -0.1700
Data Index: 2661754 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.2629. Min Act: -0.1700
Data Index: 4638215 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.2629. Min Act: -0.1700
Data Index: 5297967 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.2004. Min Act: -0.1700
Data Index: 7638 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.2004. Min Act: -0.1700
Data Index: 4232718 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.2004. Min Act: -0.1700
Data Index: 2391947 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.2629. Min Act: -0.1700
Data Index: 5665486 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.1379. Min Act: -0.1700
Data Index: 4792989 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.1379. Min Act: -0.1700
Data Index: 2661753 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.1379. Min Act: -0.1700
Data Index: 8148231 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.0754. Min Act: -0.1700
Data Index: 3568608 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.1379. Min Act: -0.1700
Data Index: 3515413 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.1379. Min Act: -0.1700
Data Index: 1429200 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.1379. Min Act: -0.1700
Data Index: 4892635 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8879. Min Range: -7.8879
Max Act: 7.1379. Min Act: -0.1700
Data Index: 1750853 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19