Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1853 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0705. Min Range: -2.0705
Max Act: 2.0705. Min Act: -0.1700
Data Index: 2863552 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9863. Min Act: -0.1700
Data Index: 2403514 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9184. Min Act: -0.1700
Data Index: 3462898 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9184. Min Act: -0.1700
Data Index: 7115030 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9013. Min Act: -0.1700
Data Index: 3134510 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.8843. Min Act: -0.1700
Data Index: 3792012 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.8843. Min Act: -0.1700
Data Index: 3399139 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.8843. Min Act: -0.1700
Data Index: 3266356 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9013. Min Act: -0.1700
Data Index: 7263048 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.8843. Min Act: -0.1700
Data Index: 7532503 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.8672. Min Act: -0.1700
Data Index: 7921679 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.8672. Min Act: -0.1700
Data Index: 3221023 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.8672. Min Act: -0.1700
Data Index: 4225427 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.8672. Min Act: -0.1700
Data Index: 5852178 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.8672. Min Act: -0.1700
Data Index: 8203736 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.8501. Min Act: -0.1700
Data Index: 1175602 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.8501. Min Act: -0.1700
Data Index: 2461598 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.8501. Min Act: -0.1700
Data Index: 8382001 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.8329. Min Act: -0.1700
Data Index: 7784967 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.8329. Min Act: -0.1700
Data Index: 5673168 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19