Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2078 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.5924. Min Act: -0.1700
Data Index: 6140378 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.5611. Min Act: -0.1699
Data Index: 815402 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.5299. Min Act: -0.1700
Data Index: 1469618 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.4361. Min Act: -0.1700
Data Index: 6396450 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.4361. Min Act: -0.1700
Data Index: 4184596 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.4361. Min Act: -0.1698
Data Index: 4466613 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.4049. Min Act: -0.1700
Data Index: 3060845 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.4049. Min Act: -0.1700
Data Index: 3817300 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.4049. Min Act: -0.1700
Data Index: 7003332 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.4049. Min Act: -0.1700
Data Index: 8758497 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.4049. Min Act: -0.1700
Data Index: 2416165 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.4049. Min Act: -0.1700
Data Index: 7058509 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.4049. Min Act: -0.1700
Data Index: 7966519 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.3736. Min Act: -0.1700
Data Index: 6594790 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.3736. Min Act: -0.1700
Data Index: 6184828 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.3424. Min Act: -0.1700
Data Index: 8408843 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.3736. Min Act: -0.1698
Data Index: 1907939 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.3111. Min Act: -0.1700
Data Index: 6386194 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.3111. Min Act: -0.1700
Data Index: 4711088 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5924. Min Range: -6.5924
Max Act: 6.3424. Min Act: -0.1700
Data Index: 2890770 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19