Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3247 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.3988. Min Act: -0.1700
Data Index: 5541936 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.3824. Min Act: -0.1682
Data Index: 1905792 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.3497. Min Act: -0.1700
Data Index: 6080721 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.3497. Min Act: -0.1700
Data Index: 7685715 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.3333. Min Act: -0.1700
Data Index: 6093864 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.3333. Min Act: -0.1700
Data Index: 30080 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.3169. Min Act: -0.1700
Data Index: 2930505 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.2840. Min Act: -0.1700
Data Index: 6460673 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.2840. Min Act: -0.1700
Data Index: 3720604 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.2840. Min Act: -0.1700
Data Index: 7255105 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.2840. Min Act: -0.1700
Data Index: 386005 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.2345. Min Act: -0.1700
Data Index: 2713213 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.2510. Min Act: -0.1700
Data Index: 2837026 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.2510. Min Act: -0.1700
Data Index: 1922985 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.2510. Min Act: -0.1700
Data Index: 4193092 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.2345. Min Act: -0.1700
Data Index: 3733596 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.2345. Min Act: -0.1700
Data Index: 5716305 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.2345. Min Act: -0.1696
Data Index: 1219589 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.2345. Min Act: -0.1700
Data Index: 1098657 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3988. Min Range: -2.3988
Max Act: 2.2345. Min Act: -0.1699
Data Index: 6266370 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19