Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3006 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.3458. Min Act: -0.1700
Data Index: 280247 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.3145. Min Act: -0.1696
Data Index: 7016320 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.2988. Min Act: -0.1698
Data Index: 7018343 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.2831. Min Act: -0.1699
Data Index: 6126173 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.2831. Min Act: -0.1700
Data Index: 1774803 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.2831. Min Act: -0.1692
Data Index: 6040045 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.2831. Min Act: -0.1700
Data Index: 4136002 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.2831. Min Act: -0.1700
Data Index: 8415388 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.2517. Min Act: -0.1700
Data Index: 1406609 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.2359. Min Act: -0.1700
Data Index: 3340149 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.2674. Min Act: -0.1700
Data Index: 593654 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.2517. Min Act: -0.1700
Data Index: 5143425 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.2359. Min Act: -0.1700
Data Index: 816072 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.2359. Min Act: -0.1700
Data Index: 5752902 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.2359. Min Act: -0.1700
Data Index: 4178208 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.2359. Min Act: -0.1568
Data Index: 2285031 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.2359. Min Act: -0.1678
Data Index: 957952 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.2359. Min Act: -0.1697
Data Index: 6643422 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.2359. Min Act: -0.1700
Data Index: 6882913 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3458. Min Range: -3.3458
Max Act: 3.2359. Min Act: -0.1700
Data Index: 3194353 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19