Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 724 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.6985. Min Act: -0.1700
Data Index: 5752747 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.7159. Min Act: -0.1700
Data Index: 4260736 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.6464. Min Act: -0.1700
Data Index: 2138468 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.6812. Min Act: -0.1700
Data Index: 8130696 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.6638. Min Act: -0.1700
Data Index: 853208 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.6290. Min Act: -0.1700
Data Index: 1202089 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.6290. Min Act: -0.1700
Data Index: 1093237 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.6464. Min Act: -0.1700
Data Index: 2776768 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.6115. Min Act: -0.1700
Data Index: 5267554 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.5941. Min Act: -0.1700
Data Index: 1699958 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.5941. Min Act: -0.1699
Data Index: 8318258 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.5766. Min Act: -0.1700
Data Index: 2304643 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.5766. Min Act: -0.1699
Data Index: 7990603 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.5941. Min Act: -0.1700
Data Index: 316110 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.5766. Min Act: -0.1700
Data Index: 172059 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.5591. Min Act: -0.1700
Data Index: 4723897 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.5766. Min Act: -0.1700
Data Index: 7365982 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.5416. Min Act: -0.1700
Data Index: 6426554 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.5591. Min Act: -0.1700
Data Index: 6266727 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7159. Min Range: -1.7159
Max Act: 1.5591. Min Act: -0.1700
Data Index: 8181358 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19