Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5070 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5930. Min Act: -0.1700
Data Index: 1027823 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5769. Min Act: -0.1700
Data Index: 1692028 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5930. Min Act: -0.1700
Data Index: 7202188 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5608. Min Act: -0.1700
Data Index: 4951296 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5769. Min Act: -0.1700
Data Index: 1628226 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5608. Min Act: -0.1700
Data Index: 4588147 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5608. Min Act: -0.1700
Data Index: 8400721 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5608. Min Act: -0.1700
Data Index: 7954525 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5608. Min Act: -0.1700
Data Index: 8582117 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5285. Min Act: -0.1700
Data Index: 4321493 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5285. Min Act: -0.1700
Data Index: 5086556 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5769. Min Act: -0.1700
Data Index: 8809125 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5446. Min Act: -0.1700
Data Index: 2315362 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5446. Min Act: -0.1700
Data Index: 8376221 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5285. Min Act: -0.1700
Data Index: 6006518 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5123. Min Act: -0.1700
Data Index: 7585905 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5285. Min Act: -0.1700
Data Index: 4381765 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5285. Min Act: -0.1700
Data Index: 4560841 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5285. Min Act: -0.1700
Data Index: 8118976 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5930. Min Range: -2.5930
Max Act: 2.5123. Min Act: -0.1700
Data Index: 5940847 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19