Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3570 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0959. Min Range: -5.0959
Max Act: 5.0959. Min Act: -0.1700
Data Index: 4292817 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0959. Min Range: -5.0959
Max Act: 4.9397. Min Act: -0.1700
Data Index: 6584337 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0959. Min Range: -5.0959
Max Act: 4.9397. Min Act: -0.1700
Data Index: 6350092 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0959. Min Range: -5.0959
Max Act: 4.9397. Min Act: -0.1700
Data Index: 2176322 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0959. Min Range: -5.0959
Max Act: 4.9397. Min Act: -0.1700
Data Index: 6527995 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0959. Min Range: -5.0959
Max Act: 4.8772. Min Act: -0.1700
Data Index: 2969280 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0959. Min Range: -5.0959
Max Act: 4.9084. Min Act: -0.1700
Data Index: 4893969 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0959. Min Range: -5.0959
Max Act: 4.8772. Min Act: -0.1700
Data Index: 2794287 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0959. Min Range: -5.0959
Max Act: 4.8772. Min Act: -0.1700
Data Index: 450122 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0959. Min Range: -5.0959
Max Act: 4.8772. Min Act: -0.1700
Data Index: 7970827 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0959. Min Range: -5.0959
Max Act: 4.8772. Min Act: -0.1700
Data Index: 1558640 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0959. Min Range: -5.0959
Max Act: 4.8772. Min Act: -0.1700
Data Index: 6004882 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0959. Min Range: -5.0959
Max Act: 4.8772. Min Act: -0.1700
Data Index: 6514369 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0959. Min Range: -5.0959
Max Act: 4.8459. Min Act: -0.1700
Data Index: 2966373 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0959. Min Range: -5.0959
Max Act: 4.8459. Min Act: -0.1700
Data Index: 7219231 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0959. Min Range: -5.0959
Max Act: 4.8147. Min Act: -0.1700
Data Index: 658633 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0959. Min Range: -5.0959
Max Act: 4.8147. Min Act: -0.1700
Data Index: 1969969 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0959. Min Range: -5.0959
Max Act: 4.8147. Min Act: -0.1700
Data Index: 4290130 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0959. Min Range: -5.0959
Max Act: 4.8459. Min Act: -0.1700
Data Index: 6673315 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0959. Min Range: -5.0959
Max Act: 4.8147. Min Act: -0.1700
Data Index: 6761254 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19