Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2959 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.9517. Min Act: -0.1700
Data Index: 1376846 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.7642. Min Act: -0.1700
Data Index: 6313761 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.7642. Min Act: -0.1700
Data Index: 5529372 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.7330. Min Act: -0.1700
Data Index: 2535696 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.7017. Min Act: -0.1700
Data Index: 6012043 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.6705. Min Act: -0.1700
Data Index: 5501140 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.6392. Min Act: -0.1700
Data Index: 2853784 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.6705. Min Act: -0.1700
Data Index: 4733567 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.6392. Min Act: -0.1700
Data Index: 437173 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.6080. Min Act: -0.1700
Data Index: 8800187 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.6080. Min Act: -0.1700
Data Index: 5430884 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.5767. Min Act: -0.1700
Data Index: 1911789 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.5455. Min Act: -0.1700
Data Index: 713045 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.5142. Min Act: -0.1700
Data Index: 301160 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.5142. Min Act: -0.1700
Data Index: 2500873 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.5142. Min Act: -0.1700
Data Index: 2203048 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.5142. Min Act: -0.1700
Data Index: 2500554 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.4517. Min Act: -0.1700
Data Index: 5098602 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.4830. Min Act: -0.1700
Data Index: 3442683 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9517. Min Range: -6.9517
Max Act: 6.4830. Min Act: -0.1700
Data Index: 3783025 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19