Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3441 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.6869. Min Act: -0.1700
Data Index: 5234996 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.6557. Min Act: -0.1699
Data Index: 1095853 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.6557. Min Act: -0.1689
Data Index: 6564095 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.6557. Min Act: -0.1697
Data Index: 5623400 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.6869. Min Act: -0.1694
Data Index: 5541320 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.6557. Min Act: -0.1680
Data Index: 5282983 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.6869. Min Act: -0.1700
Data Index: 3043012 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.6557. Min Act: -0.1697
Data Index: 4663389 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.6557. Min Act: -0.1690
Data Index: 294564 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.6869. Min Act: -0.1700
Data Index: 293437 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.6557. Min Act: -0.1700
Data Index: 3586704 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.6869. Min Act: -0.1696
Data Index: 8140007 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.6244. Min Act: -0.1700
Data Index: 6046732 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5932. Min Act: -0.1700
Data Index: 570773 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5619. Min Act: -0.1700
Data Index: 8149133 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5619. Min Act: -0.1700
Data Index: 4066252 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5619. Min Act: -0.1700
Data Index: 3825272 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5619. Min Act: -0.1700
Data Index: 5840060 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5619. Min Act: -0.1692
Data Index: 959034 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5619. Min Act: -0.1700
Data Index: 1074104 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19