Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1798 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.8125. Min Act: -0.1700
Data Index: 4755856 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.7500. Min Act: -0.1700
Data Index: 2020580 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.6563. Min Act: -0.1700
Data Index: 2025640 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.6563. Min Act: -0.1700
Data Index: 4607374 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.6250. Min Act: -0.1700
Data Index: 1941912 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.5625. Min Act: -0.1700
Data Index: 7279258 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.5625. Min Act: -0.1700
Data Index: 297496 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.5000. Min Act: -0.1700
Data Index: 6953124 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.5625. Min Act: -0.1700
Data Index: 1113275 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.4688. Min Act: -0.1700
Data Index: 4091911 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.5313. Min Act: -0.1700
Data Index: 8559617 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.5000. Min Act: -0.1700
Data Index: 5855944 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.4688. Min Act: -0.1700
Data Index: 5003379 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.4375. Min Act: -0.1700
Data Index: 1608143 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.4375. Min Act: -0.1700
Data Index: 3783613 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.4688. Min Act: -0.1700
Data Index: 7003184 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.4688. Min Act: -0.1700
Data Index: 2409817 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.4375. Min Act: -0.1700
Data Index: 1721214 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.4375. Min Act: -0.1700
Data Index: 4906856 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.4063. Min Act: -0.1700
Data Index: 6953130 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19