Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 649 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.8028. Min Act: -0.1700
Data Index: 4507879 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.7869. Min Act: -0.1700
Data Index: 8631746 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.7869. Min Act: -0.1700
Data Index: 8673601 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.7709. Min Act: -0.1700
Data Index: 8044123 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.7709. Min Act: -0.1700
Data Index: 4657297 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.7709. Min Act: -0.1700
Data Index: 3622819 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.7709. Min Act: -0.1700
Data Index: 4052035 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.7709. Min Act: -0.1700
Data Index: 803935 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.7709. Min Act: -0.1700
Data Index: 1383952 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.7550. Min Act: -0.1700
Data Index: 6850071 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.7550. Min Act: -0.1700
Data Index: 408812 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.7550. Min Act: -0.1700
Data Index: 4507881 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.7550. Min Act: -0.1700
Data Index: 6532704 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.7550. Min Act: -0.1700
Data Index: 6330197 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.7550. Min Act: -0.1700
Data Index: 4507869 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.7709. Min Act: -0.1700
Data Index: 6330198 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.7550. Min Act: -0.1700
Data Index: 3692524 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.7550. Min Act: -0.1700
Data Index: 3612051 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.7550. Min Act: -0.1700
Data Index: 3470087 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8028. Min Range: -2.8028
Max Act: 2.7550. Min Act: -0.1700
Data Index: 1047956 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19