Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2077. Min Range: -4.2077
Max Act: 4.2077. Min Act: -0.1700
Data Index: 5138089 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2077. Min Range: -4.2077
Max Act: 4.1139. Min Act: -0.1700
Data Index: 2984191 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2077. Min Range: -4.2077
Max Act: 4.0827. Min Act: -0.1700
Data Index: 5233665 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2077. Min Range: -4.2077
Max Act: 3.9889. Min Act: -0.1700
Data Index: 2508929 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2077. Min Range: -4.2077
Max Act: 3.9889. Min Act: -0.1700
Data Index: 4842240 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2077. Min Range: -4.2077
Max Act: 4.0202. Min Act: -0.1700
Data Index: 7218464 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2077. Min Range: -4.2077
Max Act: 3.9576. Min Act: -0.1700
Data Index: 1058097 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2077. Min Range: -4.2077
Max Act: 4.0202. Min Act: -0.1700
Data Index: 422759 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2077. Min Range: -4.2077
Max Act: 3.9576. Min Act: -0.1700
Data Index: 2796676 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2077. Min Range: -4.2077
Max Act: 3.9889. Min Act: -0.1700
Data Index: 6789792 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2077. Min Range: -4.2077
Max Act: 3.9576. Min Act: -0.1700
Data Index: 7791700 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2077. Min Range: -4.2077
Max Act: 3.9576. Min Act: -0.1700
Data Index: 151904 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2077. Min Range: -4.2077
Max Act: 3.9576. Min Act: -0.1700
Data Index: 5589321 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2077. Min Range: -4.2077
Max Act: 3.9889. Min Act: -0.1700
Data Index: 412296 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2077. Min Range: -4.2077
Max Act: 3.9576. Min Act: -0.1700
Data Index: 216885 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2077. Min Range: -4.2077
Max Act: 3.8951. Min Act: -0.1700
Data Index: 5858899 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2077. Min Range: -4.2077
Max Act: 3.9264. Min Act: -0.1700
Data Index: 965619 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2077. Min Range: -4.2077
Max Act: 3.9264. Min Act: -0.1700
Data Index: 4835068 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2077. Min Range: -4.2077
Max Act: 3.9264. Min Act: -0.1700
Data Index: 487251 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2077. Min Range: -4.2077
Max Act: 3.9264. Min Act: -0.1700
Data Index: 1788727 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19