Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3484 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.9309. Min Act: -0.1700
Data Index: 958525 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.6497. Min Act: -0.1700
Data Index: 4662438 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.3997. Min Act: -0.1700
Data Index: 1686809 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.3372. Min Act: -0.1700
Data Index: 2715219 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.3372. Min Act: -0.1700
Data Index: 174441 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.2747. Min Act: -0.1700
Data Index: 1077227 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.2122. Min Act: -0.1700
Data Index: 2578214 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.1497. Min Act: -0.1700
Data Index: 1989794 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.1809. Min Act: -0.1700
Data Index: 6059114 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.1809. Min Act: -0.1700
Data Index: 3748168 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.1809. Min Act: -0.1700
Data Index: 8060364 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.1809. Min Act: -0.1700
Data Index: 7316312 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.1809. Min Act: -0.1700
Data Index: 7374547 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.1497. Min Act: -0.1700
Data Index: 2097943 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.1497. Min Act: -0.1700
Data Index: 7569003 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.1184. Min Act: -0.1700
Data Index: 3559834 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.1184. Min Act: -0.1700
Data Index: 3893291 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.0872. Min Act: -0.1700
Data Index: 5748092 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.0872. Min Act: -0.1700
Data Index: 4084949 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9309. Min Range: -7.9309
Max Act: 7.0247. Min Act: -0.1700
Data Index: 2523764 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19