Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3802 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1699
Data Index: 2645337 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1693
Data Index: 1614753 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1571
Data Index: 1343039 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1636
Data Index: 729201 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1657
Data Index: 1304166 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1695
Data Index: 5898791 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1696
Data Index: 5348986 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1599
Data Index: 666017 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1700
Data Index: 4036035 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1692
Data Index: 1223458 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1698
Data Index: 6335618 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1681
Data Index: 5905346 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1695
Data Index: 3539915 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1670
Data Index: 4992688 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1571
Data Index: 1005132 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1700
Data Index: 1001635 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1697
Data Index: 1551265 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1696
Data Index: 2951559 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1656
Data Index: 595675 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7461. Min Range: -0.7461
Max Act: 0.7461. Min Act: -0.1697
Data Index: 6071480 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19