Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4780 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.9053. Min Act: -0.1700
Data Index: 7214235 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.8577. Min Act: -0.1700
Data Index: 7251804 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.8577. Min Act: -0.1700
Data Index: 3845015 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.8259. Min Act: -0.1700
Data Index: 4693222 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.8100. Min Act: -0.1700
Data Index: 3861841 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.8100. Min Act: -0.1700
Data Index: 3454806 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.7781. Min Act: -0.1700
Data Index: 7964946 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.7781. Min Act: -0.1700
Data Index: 38522 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.7781. Min Act: -0.1700
Data Index: 584533 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.7622. Min Act: -0.1700
Data Index: 2799955 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.7462. Min Act: -0.1700
Data Index: 8264889 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.7622. Min Act: -0.1700
Data Index: 8352929 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.7143. Min Act: -0.1700
Data Index: 345320 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.7143. Min Act: -0.1700
Data Index: 5237409 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.7143. Min Act: -0.1700
Data Index: 6656750 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.7143. Min Act: -0.1700
Data Index: 8352928 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.6983. Min Act: -0.1700
Data Index: 4575898 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.6983. Min Act: -0.1700
Data Index: 4031116 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.6983. Min Act: -0.1700
Data Index: 5073707 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9053. Min Range: -2.9053
Max Act: 2.6983. Min Act: -0.1700
Data Index: 6199845 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19