Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5953 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0551. Min Range: -6.0551
Max Act: 6.0551. Min Act: -0.1700
Data Index: 5733520 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0551. Min Range: -6.0551
Max Act: 5.7113. Min Act: -0.1700
Data Index: 7569118 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0551. Min Range: -6.0551
Max Act: 5.5863. Min Act: -0.1696
Data Index: 4116224 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0551. Min Range: -6.0551
Max Act: 5.5551. Min Act: -0.1700
Data Index: 1841688 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0551. Min Range: -6.0551
Max Act: 5.4926. Min Act: -0.1699
Data Index: 7611792 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0551. Min Range: -6.0551
Max Act: 5.4926. Min Act: -0.1700
Data Index: 3307993 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0551. Min Range: -6.0551
Max Act: 5.4301. Min Act: -0.1700
Data Index: 5908545 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0551. Min Range: -6.0551
Max Act: 5.3676. Min Act: -0.1699
Data Index: 7401349 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0551. Min Range: -6.0551
Max Act: 5.3363. Min Act: -0.1553
Data Index: 4962920 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0551. Min Range: -6.0551
Max Act: 5.3363. Min Act: -0.1631
Data Index: 3216051 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0551. Min Range: -6.0551
Max Act: 5.3051. Min Act: -0.1700
Data Index: 2905651 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0551. Min Range: -6.0551
Max Act: 5.3051. Min Act: -0.1700
Data Index: 6754558 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0551. Min Range: -6.0551
Max Act: 5.3051. Min Act: -0.1700
Data Index: 1982758 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0551. Min Range: -6.0551
Max Act: 5.3051. Min Act: -0.1700
Data Index: 8201234 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0551. Min Range: -6.0551
Max Act: 5.3051. Min Act: -0.1700
Data Index: 7499802 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0551. Min Range: -6.0551
Max Act: 5.3051. Min Act: -0.1700
Data Index: 8476652 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0551. Min Range: -6.0551
Max Act: 5.2738. Min Act: -0.1700
Data Index: 7876911 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0551. Min Range: -6.0551
Max Act: 5.2738. Min Act: -0.1700
Data Index: 6940583 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0551. Min Range: -6.0551
Max Act: 5.2738. Min Act: -0.1671
Data Index: 7473808 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0551. Min Range: -6.0551
Max Act: 5.2426. Min Act: -0.1700
Data Index: 181430 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19