Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0169. Min Range: -7.0169
Max Act: 7.0169. Min Act: -0.1700
Data Index: 6306492 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0169. Min Range: -7.0169
Max Act: 6.8919. Min Act: -0.1700
Data Index: 7775394 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0169. Min Range: -7.0169
Max Act: 6.8294. Min Act: -0.1700
Data Index: 1112208 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0169. Min Range: -7.0169
Max Act: 6.8294. Min Act: -0.1700
Data Index: 2764835 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0169. Min Range: -7.0169
Max Act: 6.7669. Min Act: -0.1700
Data Index: 7649631 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0169. Min Range: -7.0169
Max Act: 6.7669. Min Act: -0.1700
Data Index: 8478820 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0169. Min Range: -7.0169
Max Act: 6.7356. Min Act: -0.1700
Data Index: 2235920 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0169. Min Range: -7.0169
Max Act: 6.7044. Min Act: -0.1700
Data Index: 4227830 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0169. Min Range: -7.0169
Max Act: 6.7044. Min Act: -0.1700
Data Index: 6446308 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0169. Min Range: -7.0169
Max Act: 6.7044. Min Act: -0.1700
Data Index: 3629779 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0169. Min Range: -7.0169
Max Act: 6.6106. Min Act: -0.1700
Data Index: 2611419 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0169. Min Range: -7.0169
Max Act: 6.6106. Min Act: -0.1700
Data Index: 6220235 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0169. Min Range: -7.0169
Max Act: 6.6106. Min Act: -0.1700
Data Index: 3036036 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0169. Min Range: -7.0169
Max Act: 6.6106. Min Act: -0.1700
Data Index: 6358086 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0169. Min Range: -7.0169
Max Act: 6.5794. Min Act: -0.1700
Data Index: 5056626 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0169. Min Range: -7.0169
Max Act: 6.5481. Min Act: -0.1700
Data Index: 2596226 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0169. Min Range: -7.0169
Max Act: 6.5481. Min Act: -0.1700
Data Index: 1071076 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0169. Min Range: -7.0169
Max Act: 6.5169. Min Act: -0.1700
Data Index: 773811 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0169. Min Range: -7.0169
Max Act: 6.4856. Min Act: -0.1700
Data Index: 2788009 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0169. Min Range: -7.0169
Max Act: 6.4856. Min Act: -0.1700
Data Index: 3446199 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19