Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3785 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.7705. Min Act: -0.1700
Data Index: 1989537 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.7446. Min Act: -0.1700
Data Index: 6058390 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.7618. Min Act: -0.1700
Data Index: 2816166 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.7273. Min Act: -0.1700
Data Index: 7505057 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.7186. Min Act: -0.1700
Data Index: 6287571 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.7186. Min Act: -0.1700
Data Index: 2532599 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.7100. Min Act: -0.1700
Data Index: 1004696 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.7013. Min Act: -0.1700
Data Index: 260906 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.7013. Min Act: -0.1700
Data Index: 2489540 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.7013. Min Act: -0.1700
Data Index: 6719846 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.7013. Min Act: -0.1700
Data Index: 92742 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.7100. Min Act: -0.1700
Data Index: 4692070 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.7013. Min Act: -0.1700
Data Index: 5818524 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.7013. Min Act: -0.1700
Data Index: 7164220 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.6839. Min Act: -0.1700
Data Index: 806980 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.6752. Min Act: -0.1700
Data Index: 8138968 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.6926. Min Act: -0.1700
Data Index: 6156929 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.6839. Min Act: -0.1700
Data Index: 1704792 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.6839. Min Act: -0.1700
Data Index: 3488209 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7705. Min Range: -1.7705
Max Act: 1.6926. Min Act: -0.1700
Data Index: 8206966 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19