Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.9738. Min Act: -0.1700
Data Index: 2383113 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.9738. Min Act: -0.1700
Data Index: 4238460 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.8800. Min Act: -0.1700
Data Index: 3635806 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.8487. Min Act: -0.1700
Data Index: 668715 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.8487. Min Act: -0.1700
Data Index: 4071611 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.8018. Min Act: -0.1700
Data Index: 1207124 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.8174. Min Act: -0.1700
Data Index: 3701901 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.8018. Min Act: -0.1700
Data Index: 6054665 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.7861. Min Act: -0.1700
Data Index: 8346671 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.7861. Min Act: -0.1700
Data Index: 8342128 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.7549. Min Act: -0.1700
Data Index: 3919722 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.7705. Min Act: -0.1700
Data Index: 7111196 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.7549. Min Act: -0.1700
Data Index: 3522935 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.7392. Min Act: -0.1700
Data Index: 815242 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.7392. Min Act: -0.1700
Data Index: 1586704 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.7392. Min Act: -0.1700
Data Index: 4117215 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.7392. Min Act: -0.1700
Data Index: 4896947 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.7079. Min Act: -0.1700
Data Index: 4741847 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.7079. Min Act: -0.1700
Data Index: 6962310 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9738. Min Range: -3.9738
Max Act: 3.6923. Min Act: -0.1700
Data Index: 4738890 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19