Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4296 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.9052. Min Act: -0.1700
Data Index: 6886175 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.9052. Min Act: -0.1700
Data Index: 141595 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.8739. Min Act: -0.1700
Data Index: 5568926 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.7489. Min Act: -0.1700
Data Index: 2012425 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.7489. Min Act: -0.1700
Data Index: 4342181 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.7489. Min Act: -0.1700
Data Index: 6335454 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.7802. Min Act: -0.1700
Data Index: 3575939 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.7489. Min Act: -0.1700
Data Index: 2923657 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.7177. Min Act: -0.1700
Data Index: 6218547 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.6552. Min Act: -0.1700
Data Index: 1885524 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.6552. Min Act: -0.1700
Data Index: 7747780 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.6239. Min Act: -0.1700
Data Index: 809991 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.6239. Min Act: -0.1700
Data Index: 5219951 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.6239. Min Act: -0.1700
Data Index: 3499739 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.6239. Min Act: -0.1700
Data Index: 1204087 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.5927. Min Act: -0.1700
Data Index: 3872930 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.5927. Min Act: -0.1700
Data Index: 5841902 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.6239. Min Act: -0.1700
Data Index: 4067599 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.5614. Min Act: -0.1700
Data Index: 4941487 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9052. Min Range: -6.9052
Max Act: 6.5614. Min Act: -0.1700
Data Index: 1016760 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19