Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6206 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3670. Min Range: -8.3670
Max Act: 8.3670. Min Act: -0.1700
Data Index: 2514933 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3670. Min Range: -8.3670
Max Act: 8.1170. Min Act: -0.1700
Data Index: 6599270 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3670. Min Range: -8.3670
Max Act: 8.1170. Min Act: -0.1700
Data Index: 8002639 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3670. Min Range: -8.3670
Max Act: 7.8045. Min Act: -0.1700
Data Index: 6248179 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3670. Min Range: -8.3670
Max Act: 7.8045. Min Act: -0.1700
Data Index: 4763578 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3670. Min Range: -8.3670
Max Act: 7.8045. Min Act: -0.1700
Data Index: 2546318 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3670. Min Range: -8.3670
Max Act: 7.7420. Min Act: -0.1700
Data Index: 1932319 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3670. Min Range: -8.3670
Max Act: 7.6795. Min Act: -0.1700
Data Index: 3040908 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3670. Min Range: -8.3670
Max Act: 7.6795. Min Act: -0.1700
Data Index: 1773372 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3670. Min Range: -8.3670
Max Act: 7.6795. Min Act: -0.1700
Data Index: 915473 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3670. Min Range: -8.3670
Max Act: 7.7420. Min Act: -0.1700
Data Index: 3934302 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3670. Min Range: -8.3670
Max Act: 7.6170. Min Act: -0.1700
Data Index: 518113 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3670. Min Range: -8.3670
Max Act: 7.6170. Min Act: -0.1700
Data Index: 4321979 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3670. Min Range: -8.3670
Max Act: 7.5858. Min Act: -0.1700
Data Index: 2184452 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3670. Min Range: -8.3670
Max Act: 7.5858. Min Act: -0.1700
Data Index: 2398014 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3670. Min Range: -8.3670
Max Act: 7.5545. Min Act: -0.1700
Data Index: 1085982 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3670. Min Range: -8.3670
Max Act: 7.5545. Min Act: -0.1700
Data Index: 8359726 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3670. Min Range: -8.3670
Max Act: 7.5545. Min Act: -0.1700
Data Index: 2165716 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3670. Min Range: -8.3670
Max Act: 7.5545. Min Act: -0.1700
Data Index: 3234743 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3670. Min Range: -8.3670
Max Act: 7.5233. Min Act: -0.1700
Data Index: 5362308 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19