Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1458 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3035. Min Range: -5.3035
Max Act: 5.3035. Min Act: -0.1700
Data Index: 5365703 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3035. Min Range: -5.3035
Max Act: 5.1785. Min Act: -0.1700
Data Index: 107316 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3035. Min Range: -5.3035
Max Act: 5.1160. Min Act: -0.1700
Data Index: 1172539 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3035. Min Range: -5.3035
Max Act: 5.0222. Min Act: -0.1700
Data Index: 2134062 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3035. Min Range: -5.3035
Max Act: 4.9597. Min Act: -0.1700
Data Index: 4218161 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3035. Min Range: -5.3035
Max Act: 4.9597. Min Act: -0.1700
Data Index: 3046016 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3035. Min Range: -5.3035
Max Act: 4.9285. Min Act: -0.1699
Data Index: 8516398 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3035. Min Range: -5.3035
Max Act: 4.9285. Min Act: -0.1700
Data Index: 1167735 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3035. Min Range: -5.3035
Max Act: 4.8972. Min Act: -0.1700
Data Index: 6185503 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3035. Min Range: -5.3035
Max Act: 4.8972. Min Act: -0.1700
Data Index: 1818676 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3035. Min Range: -5.3035
Max Act: 4.8972. Min Act: -0.1700
Data Index: 5538563 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3035. Min Range: -5.3035
Max Act: 4.8660. Min Act: -0.1700
Data Index: 5595917 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3035. Min Range: -5.3035
Max Act: 4.8347. Min Act: -0.1700
Data Index: 7861771 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3035. Min Range: -5.3035
Max Act: 4.8347. Min Act: -0.1700
Data Index: 7914123 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3035. Min Range: -5.3035
Max Act: 4.8347. Min Act: -0.1700
Data Index: 8498454 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3035. Min Range: -5.3035
Max Act: 4.8035. Min Act: -0.1700
Data Index: 6354704 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3035. Min Range: -5.3035
Max Act: 4.7722. Min Act: -0.1700
Data Index: 7691945 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3035. Min Range: -5.3035
Max Act: 4.7722. Min Act: -0.1700
Data Index: 3295734 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3035. Min Range: -5.3035
Max Act: 4.7722. Min Act: -0.1700
Data Index: 6315281 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3035. Min Range: -5.3035
Max Act: 4.7722. Min Act: -0.1700
Data Index: 900219 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19