Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2672 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1213. Min Range: -6.1213
Max Act: 6.1213. Min Act: -0.1700
Data Index: 4102261 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1213. Min Range: -6.1213
Max Act: 6.1213. Min Act: -0.1700
Data Index: 3832197 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1213. Min Range: -6.1213
Max Act: 6.1213. Min Act: -0.1700
Data Index: 3577380 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1213. Min Range: -6.1213
Max Act: 6.0900. Min Act: -0.1700
Data Index: 6029348 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1213. Min Range: -6.1213
Max Act: 5.9650. Min Act: -0.1700
Data Index: 1548133 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1213. Min Range: -6.1213
Max Act: 5.8713. Min Act: -0.1700
Data Index: 249904 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1213. Min Range: -6.1213
Max Act: 5.8400. Min Act: -0.1700
Data Index: 2066554 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1213. Min Range: -6.1213
Max Act: 5.8088. Min Act: -0.1700
Data Index: 1623279 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1213. Min Range: -6.1213
Max Act: 5.8088. Min Act: -0.1700
Data Index: 3338904 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1213. Min Range: -6.1213
Max Act: 5.7775. Min Act: -0.1700
Data Index: 2268064 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1213. Min Range: -6.1213
Max Act: 5.7775. Min Act: -0.1700
Data Index: 5148299 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1213. Min Range: -6.1213
Max Act: 5.8088. Min Act: -0.1700
Data Index: 3012533 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1213. Min Range: -6.1213
Max Act: 5.7775. Min Act: -0.1700
Data Index: 5662104 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1213. Min Range: -6.1213
Max Act: 5.7775. Min Act: -0.1700
Data Index: 2677718 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1213. Min Range: -6.1213
Max Act: 5.7463. Min Act: -0.1700
Data Index: 5930914 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1213. Min Range: -6.1213
Max Act: 5.7463. Min Act: -0.1700
Data Index: 7102977 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1213. Min Range: -6.1213
Max Act: 5.7463. Min Act: -0.1700
Data Index: 1223580 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1213. Min Range: -6.1213
Max Act: 5.6838. Min Act: -0.1700
Data Index: 6272932 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1213. Min Range: -6.1213
Max Act: 5.6838. Min Act: -0.1700
Data Index: 6084453 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1213. Min Range: -6.1213
Max Act: 5.6525. Min Act: -0.1700
Data Index: 828574 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19