Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3146 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.5785. Min Act: -0.1700
Data Index: 5556973 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.5160. Min Act: -0.1700
Data Index: 473214 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.3910. Min Act: -0.1700
Data Index: 875206 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.4535. Min Act: -0.1700
Data Index: 6882327 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.4535. Min Act: -0.1700
Data Index: 4494933 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.3285. Min Act: -0.1700
Data Index: 915299 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.2035. Min Act: -0.1700
Data Index: 3538508 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.2660. Min Act: -0.1700
Data Index: 3668920 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.2660. Min Act: -0.1700
Data Index: 4002937 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.2660. Min Act: -0.1700
Data Index: 5050438 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.3285. Min Act: -0.1700
Data Index: 3955113 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.2035. Min Act: -0.1700
Data Index: 902322 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.1410. Min Act: -0.1700
Data Index: 8640825 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.1410. Min Act: -0.1700
Data Index: 4123376 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.1410. Min Act: -0.1700
Data Index: 282091 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.2035. Min Act: -0.1700
Data Index: 5840325 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.1410. Min Act: -0.1700
Data Index: 3576902 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.1410. Min Act: -0.1700
Data Index: 3336009 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.1410. Min Act: -0.1700
Data Index: 1113313 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5785. Min Range: -8.5785
Max Act: 8.1098. Min Act: -0.1700
Data Index: 4098338 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19