Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4944 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.8830. Min Act: -0.1700
Data Index: 2261716 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.8518. Min Act: -0.1700
Data Index: 6859931 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.8518. Min Act: -0.1700
Data Index: 194118 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.8518. Min Act: -0.1700
Data Index: 2207929 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.7892. Min Act: -0.1700
Data Index: 1213108 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.8205. Min Act: -0.1700
Data Index: 2006275 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.8205. Min Act: -0.1700
Data Index: 5440636 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.8205. Min Act: -0.1700
Data Index: 283326 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.7580. Min Act: -0.1700
Data Index: 2745575 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.7580. Min Act: -0.1700
Data Index: 8138967 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.7580. Min Act: -0.1700
Data Index: 2155597 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.7580. Min Act: -0.1700
Data Index: 6055192 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.7892. Min Act: -0.1700
Data Index: 8004041 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.7267. Min Act: -0.1700
Data Index: 5230390 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.7267. Min Act: -0.1700
Data Index: 2284245 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.6955. Min Act: -0.1700
Data Index: 691679 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.6955. Min Act: -0.1700
Data Index: 4814611 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.6955. Min Act: -0.1700
Data Index: 4398535 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.6955. Min Act: -0.1700
Data Index: 3800992 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8830. Min Range: -4.8830
Max Act: 4.6955. Min Act: -0.1700
Data Index: 6550420 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19