Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6311 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.6729. Min Act: -0.1700
Data Index: 7685037 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.5791. Min Act: -0.1700
Data Index: 716578 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.5479. Min Act: -0.1700
Data Index: 1637589 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.5479. Min Act: -0.1700
Data Index: 5190993 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.5166. Min Act: -0.1700
Data Index: 476384 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.5479. Min Act: -0.1700
Data Index: 1637591 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.5166. Min Act: -0.1700
Data Index: 8767444 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.5166. Min Act: -0.1700
Data Index: 8806254 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.4854. Min Act: -0.1700
Data Index: 5479359 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.4541. Min Act: -0.1700
Data Index: 1585735 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.4541. Min Act: -0.1700
Data Index: 5141686 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.4541. Min Act: -0.1700
Data Index: 3666458 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.3916. Min Act: -0.1700
Data Index: 1766881 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.4541. Min Act: -0.1700
Data Index: 7762363 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.4229. Min Act: -0.1700
Data Index: 7333649 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.3916. Min Act: -0.1700
Data Index: 3218704 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.3604. Min Act: -0.1700
Data Index: 8089234 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.3604. Min Act: -0.1700
Data Index: 5112528 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.3604. Min Act: -0.1700
Data Index: 2522349 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6729. Min Range: -5.6729
Max Act: 5.3604. Min Act: -0.1700
Data Index: 1766882 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19