Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5789 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.8634. Min Act: -0.1700
Data Index: 274017 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.5035. Min Act: -0.1700
Data Index: 5223467 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.4409. Min Act: -0.1700
Data Index: 5657682 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.4095. Min Act: -0.1700
Data Index: 501601 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.4095. Min Act: -0.1700
Data Index: 5397498 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.4095. Min Act: -0.1700
Data Index: 5237978 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.3938. Min Act: -0.1700
Data Index: 4422060 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.3782. Min Act: -0.1700
Data Index: 6240041 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.3782. Min Act: -0.1700
Data Index: 4280755 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.3468. Min Act: -0.1700
Data Index: 1166784 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.3468. Min Act: -0.1700
Data Index: 8796574 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.3468. Min Act: -0.1700
Data Index: 3358673 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.3468. Min Act: -0.1700
Data Index: 6675380 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.3154. Min Act: -0.1700
Data Index: 3821220 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.3311. Min Act: -0.1700
Data Index: 3916042 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.3154. Min Act: -0.1700
Data Index: 6304459 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.3154. Min Act: -0.1700
Data Index: 1417150 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.3154. Min Act: -0.1700
Data Index: 3488728 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.2997. Min Act: -0.1700
Data Index: 6544669 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8634. Min Range: -3.8634
Max Act: 3.2997. Min Act: -0.1700
Data Index: 6390344 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #19