Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2749 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.5569. Min Act: -0.1700
Data Index: 8557780 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.5256. Min Act: -0.1700
Data Index: 6407479 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.4631. Min Act: -0.1700
Data Index: 6173197 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.4006. Min Act: -0.1700
Data Index: 4154048 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.4006. Min Act: -0.1700
Data Index: 3349002 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.4006. Min Act: -0.1700
Data Index: 3398808 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.4006. Min Act: -0.1700
Data Index: 4800975 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.4006. Min Act: -0.1700
Data Index: 5312041 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.4319. Min Act: -0.1700
Data Index: 6407477 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.3693. Min Act: -0.1700
Data Index: 3546936 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.4006. Min Act: -0.1700
Data Index: 6407473 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.4006. Min Act: -0.1700
Data Index: 2261760 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.4006. Min Act: -0.1700
Data Index: 1183968 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.3693. Min Act: -0.1700
Data Index: 3905730 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.3693. Min Act: -0.1700
Data Index: 6407480 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.3693. Min Act: -0.1700
Data Index: 5114948 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.3693. Min Act: -0.1700
Data Index: 5064700 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.3693. Min Act: -0.1700
Data Index: 6623682 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.3693. Min Act: -0.1700
Data Index: 6461516 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5569. Min Range: -4.5569
Max Act: 4.3693. Min Act: -0.1700
Data Index: 470402 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19