Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2460 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.5843. Min Act: -0.1700
Data Index: 1460149 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.5843. Min Act: -0.1700
Data Index: 3143526 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.5531. Min Act: -0.1700
Data Index: 287919 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.4593. Min Act: -0.1700
Data Index: 1139926 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.4593. Min Act: -0.1700
Data Index: 43455 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.3968. Min Act: -0.1700
Data Index: 2252824 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.3031. Min Act: -0.1700
Data Index: 6598338 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.3031. Min Act: -0.1700
Data Index: 2252827 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.2718. Min Act: -0.1700
Data Index: 2822585 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.2718. Min Act: -0.1700
Data Index: 6777583 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.2718. Min Act: -0.1700
Data Index: 6441348 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.2718. Min Act: -0.1700
Data Index: 543115 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.2718. Min Act: -0.1700
Data Index: 7425602 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.2093. Min Act: -0.1700
Data Index: 4570375 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.2093. Min Act: -0.1700
Data Index: 4682259 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.2406. Min Act: -0.1700
Data Index: 5239829 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.2093. Min Act: -0.1700
Data Index: 3674044 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.1781. Min Act: -0.1700
Data Index: 7724330 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.1781. Min Act: -0.1700
Data Index: 5525010 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5843. Min Range: -5.5843
Max Act: 5.1468. Min Act: -0.1700
Data Index: 701740 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19