Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4298 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.7982. Min Act: -0.1699
Data Index: 3693629 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.7669. Min Act: -0.1699
Data Index: 3061586 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.7357. Min Act: -0.1700
Data Index: 5907440 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.7357. Min Act: -0.1700
Data Index: 4253071 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.6732. Min Act: -0.1698
Data Index: 4237968 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.6732. Min Act: -0.1699
Data Index: 8813345 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.6107. Min Act: -0.1689
Data Index: 6813633 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.6107. Min Act: -0.1700
Data Index: 6549617 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.6107. Min Act: -0.1700
Data Index: 3984845 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.6107. Min Act: -0.1700
Data Index: 5138023 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.6107. Min Act: -0.1700
Data Index: 2476607 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.5794. Min Act: -0.1700
Data Index: 5331688 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.5482. Min Act: -0.1700
Data Index: 2861115 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.5169. Min Act: -0.1700
Data Index: 3410406 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.5794. Min Act: -0.1700
Data Index: 1567391 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.4857. Min Act: -0.1700
Data Index: 5569764 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.5169. Min Act: -0.1700
Data Index: 5299270 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.5169. Min Act: -0.1700
Data Index: 3734314 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.4857. Min Act: -0.1699
Data Index: 3929908 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7982. Min Range: -4.7982
Max Act: 4.4544. Min Act: -0.1700
Data Index: 3979486 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19