Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2971 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4017. Min Range: -7.4017
Max Act: 7.4017. Min Act: -0.1700
Data Index: 5296224 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4017. Min Range: -7.4017
Max Act: 7.2767. Min Act: -0.1700
Data Index: 6646541 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.9955. Min Act: -0.1700
Data Index: 1343482 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.8392. Min Act: -0.1700
Data Index: 1083010 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.8392. Min Act: -0.1700
Data Index: 2009612 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.7767. Min Act: -0.1700
Data Index: 7440313 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.7455. Min Act: -0.1700
Data Index: 1998201 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.7142. Min Act: -0.1700
Data Index: 2959711 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.6830. Min Act: -0.1700
Data Index: 5350096 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.6830. Min Act: -0.1700
Data Index: 2171177 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.6517. Min Act: -0.1700
Data Index: 4841113 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.6205. Min Act: -0.1700
Data Index: 4387175 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.6205. Min Act: -0.1700
Data Index: 1163964 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.6205. Min Act: -0.1700
Data Index: 2207328 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.5892. Min Act: -0.1700
Data Index: 4601333 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.5892. Min Act: -0.1700
Data Index: 8420089 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.5892. Min Act: -0.1700
Data Index: 4738763 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.5892. Min Act: -0.1700
Data Index: 94196 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.5580. Min Act: -0.1700
Data Index: 7911322 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4017. Min Range: -7.4017
Max Act: 6.5580. Min Act: -0.1700
Data Index: 3892007 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19