Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3400 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.4024. Min Act: -0.1700
Data Index: 7544209 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.3710. Min Act: -0.1700
Data Index: 881713 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.3083. Min Act: -0.1700
Data Index: 2286013 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.2926. Min Act: -0.1700
Data Index: 2484710 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.2769. Min Act: -0.1700
Data Index: 6753074 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.2769. Min Act: -0.1700
Data Index: 1025463 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.2769. Min Act: -0.1700
Data Index: 3399804 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.2611. Min Act: -0.1700
Data Index: 1057191 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.2611. Min Act: -0.1700
Data Index: 955263 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.2611. Min Act: -0.1700
Data Index: 7441071 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.2611. Min Act: -0.1700
Data Index: 7361229 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.2454. Min Act: -0.1700
Data Index: 2884010 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.2454. Min Act: -0.1700
Data Index: 1012952 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.2297. Min Act: -0.1700
Data Index: 960970 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.2454. Min Act: -0.1700
Data Index: 8793276 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.2454. Min Act: -0.1700
Data Index: 8329404 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.2297. Min Act: -0.1700
Data Index: 2742338 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.2297. Min Act: -0.1700
Data Index: 3421930 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.2297. Min Act: -0.1700
Data Index: 7162790 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4024. Min Range: -3.4024
Max Act: 3.2297. Min Act: -0.1700
Data Index: 1990859 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19