Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3342 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.3633. Min Act: -0.1700
Data Index: 2581071 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.3320. Min Act: -0.1700
Data Index: 3375205 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.3320. Min Act: -0.1700
Data Index: 5314933 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.3008. Min Act: -0.1700
Data Index: 5671260 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.3008. Min Act: -0.1700
Data Index: 1125545 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.2383. Min Act: -0.1700
Data Index: 3190845 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.2070. Min Act: -0.1700
Data Index: 4716170 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.2070. Min Act: -0.1700
Data Index: 1502449 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.1758. Min Act: -0.1700
Data Index: 5689889 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.1758. Min Act: -0.1700
Data Index: 2222946 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.1758. Min Act: -0.1700
Data Index: 4559153 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.1758. Min Act: -0.1700
Data Index: 6324674 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.1758. Min Act: -0.1700
Data Index: 8655815 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.1758. Min Act: -0.1700
Data Index: 1506581 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.1133. Min Act: -0.1700
Data Index: 2411163 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.1133. Min Act: -0.1700
Data Index: 5234827 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.1133. Min Act: -0.1700
Data Index: 8050200 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.1133. Min Act: -0.1700
Data Index: 2349613 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.0820. Min Act: -0.1700
Data Index: 6965146 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3633. Min Range: -7.3633
Max Act: 7.0820. Min Act: -0.1700
Data Index: 3749622 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19