Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2449 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1383. Min Range: -6.1383
Max Act: 6.1383. Min Act: -0.1700
Data Index: 3991705 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1383. Min Range: -6.1383
Max Act: 5.9821. Min Act: -0.1700
Data Index: 5623033 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1383. Min Range: -6.1383
Max Act: 5.8258. Min Act: -0.1700
Data Index: 427800 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1383. Min Range: -6.1383
Max Act: 5.8258. Min Act: -0.1700
Data Index: 7792576 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1383. Min Range: -6.1383
Max Act: 5.7008. Min Act: -0.1700
Data Index: 6897835 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1383. Min Range: -6.1383
Max Act: 5.6696. Min Act: -0.1700
Data Index: 7414236 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1383. Min Range: -6.1383
Max Act: 5.6383. Min Act: -0.1700
Data Index: 7682312 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1383. Min Range: -6.1383
Max Act: 5.5446. Min Act: -0.1700
Data Index: 8488817 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1383. Min Range: -6.1383
Max Act: 5.5133. Min Act: -0.1700
Data Index: 7377792 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1383. Min Range: -6.1383
Max Act: 5.5446. Min Act: -0.1700
Data Index: 4303449 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1383. Min Range: -6.1383
Max Act: 5.5446. Min Act: -0.1700
Data Index: 4150161 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1383. Min Range: -6.1383
Max Act: 5.5133. Min Act: -0.1700
Data Index: 1928845 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1383. Min Range: -6.1383
Max Act: 5.5133. Min Act: -0.1700
Data Index: 384116 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1383. Min Range: -6.1383
Max Act: 5.5133. Min Act: -0.1700
Data Index: 5122259 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1383. Min Range: -6.1383
Max Act: 5.5133. Min Act: -0.1700
Data Index: 2961104 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1383. Min Range: -6.1383
Max Act: 5.4821. Min Act: -0.1700
Data Index: 4652926 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1383. Min Range: -6.1383
Max Act: 5.4821. Min Act: -0.1700
Data Index: 985856 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1383. Min Range: -6.1383
Max Act: 5.4821. Min Act: -0.1700
Data Index: 7872448 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1383. Min Range: -6.1383
Max Act: 5.4508. Min Act: -0.1700
Data Index: 964074 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1383. Min Range: -6.1383
Max Act: 5.4196. Min Act: -0.1700
Data Index: 1792416 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19