Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5083 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0393. Min Range: -5.0393
Max Act: 5.0393. Min Act: -0.1700
Data Index: 8630209 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0393. Min Range: -5.0393
Max Act: 5.0080. Min Act: -0.1700
Data Index: 6646249 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0393. Min Range: -5.0393
Max Act: 5.0080. Min Act: -0.1700
Data Index: 5332253 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0393. Min Range: -5.0393
Max Act: 4.9768. Min Act: -0.1700
Data Index: 8245820 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0393. Min Range: -5.0393
Max Act: 4.9768. Min Act: -0.1700
Data Index: 1019738 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0393. Min Range: -5.0393
Max Act: 4.9768. Min Act: -0.1700
Data Index: 2994948 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0393. Min Range: -5.0393
Max Act: 4.9768. Min Act: -0.1700
Data Index: 1632250 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0393. Min Range: -5.0393
Max Act: 4.9455. Min Act: -0.1700
Data Index: 7654734 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0393. Min Range: -5.0393
Max Act: 4.9455. Min Act: -0.1700
Data Index: 7553990 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0393. Min Range: -5.0393
Max Act: 4.9455. Min Act: -0.1700
Data Index: 1771943 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0393. Min Range: -5.0393
Max Act: 4.9455. Min Act: -0.1700
Data Index: 7354715 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0393. Min Range: -5.0393
Max Act: 4.9455. Min Act: -0.1700
Data Index: 318926 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0393. Min Range: -5.0393
Max Act: 4.9455. Min Act: -0.1700
Data Index: 5067416 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0393. Min Range: -5.0393
Max Act: 4.9455. Min Act: -0.1700
Data Index: 4631259 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0393. Min Range: -5.0393
Max Act: 4.9455. Min Act: -0.1700
Data Index: 3643200 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0393. Min Range: -5.0393
Max Act: 4.9455. Min Act: -0.1700
Data Index: 3541088 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0393. Min Range: -5.0393
Max Act: 4.9455. Min Act: -0.1700
Data Index: 3370523 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0393. Min Range: -5.0393
Max Act: 4.9455. Min Act: -0.1700
Data Index: 1071939 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0393. Min Range: -5.0393
Max Act: 4.9455. Min Act: -0.1700
Data Index: 2295496 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0393. Min Range: -5.0393
Max Act: 4.9455. Min Act: -0.1700
Data Index: 768919 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19