Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3298 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.1473. Min Range: -17.1473
Max Act: 17.1473. Min Act: -0.1700
Data Index: 6199760 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.1473. Min Range: -17.1473
Max Act: 16.6473. Min Act: -0.1700
Data Index: 4016939 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.1473. Min Range: -17.1473
Max Act: 16.1473. Min Act: -0.1700
Data Index: 1560503 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.1473. Min Range: -17.1473
Max Act: 16.0223. Min Act: -0.1700
Data Index: 8029136 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.1473. Min Range: -17.1473
Max Act: 15.8973. Min Act: -0.1700
Data Index: 3897729 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.1473. Min Range: -17.1473
Max Act: 15.6473. Min Act: -0.1700
Data Index: 8611975 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.1473. Min Range: -17.1473
Max Act: 15.3973. Min Act: -0.1700
Data Index: 5556508 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.1473. Min Range: -17.1473
Max Act: 15.3348. Min Act: -0.1700
Data Index: 5155005 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.1473. Min Range: -17.1473
Max Act: 15.3348. Min Act: -0.1700
Data Index: 1964962 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.1473. Min Range: -17.1473
Max Act: 15.2098. Min Act: -0.1700
Data Index: 6962774 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.1473. Min Range: -17.1473
Max Act: 15.2723. Min Act: -0.1700
Data Index: 635759 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.1473. Min Range: -17.1473
Max Act: 15.2098. Min Act: -0.1700
Data Index: 4387474 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.1473. Min Range: -17.1473
Max Act: 15.2098. Min Act: -0.1700
Data Index: 5207451 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.1473. Min Range: -17.1473
Max Act: 15.1473. Min Act: -0.1700
Data Index: 2559687 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.1473. Min Range: -17.1473
Max Act: 15.1473. Min Act: -0.1700
Data Index: 6705512 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.1473. Min Range: -17.1473
Max Act: 15.0848. Min Act: -0.1700
Data Index: 834936 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.1473. Min Range: -17.1473
Max Act: 15.0848. Min Act: -0.1700
Data Index: 1108208 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.1473. Min Range: -17.1473
Max Act: 15.0848. Min Act: -0.1700
Data Index: 2441855 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.1473. Min Range: -17.1473
Max Act: 15.0223. Min Act: -0.1700
Data Index: 5522796 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.1473. Min Range: -17.1473
Max Act: 15.0848. Min Act: -0.1700
Data Index: 3725968 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19