Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1355 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.8955. Min Act: -0.1700
Data Index: 5681579 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.8642. Min Act: -0.1700
Data Index: 7479535 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.8642. Min Act: -0.1700
Data Index: 4752908 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.8017. Min Act: -0.1700
Data Index: 2578556 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.7705. Min Act: -0.1700
Data Index: 6449420 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.7705. Min Act: -0.1700
Data Index: 7002210 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.7705. Min Act: -0.1700
Data Index: 5431907 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.7705. Min Act: -0.1700
Data Index: 2383596 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.7705. Min Act: -0.1700
Data Index: 2624169 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.7392. Min Act: -0.1700
Data Index: 1104947 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.7080. Min Act: -0.1700
Data Index: 4784412 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.6767. Min Act: -0.1700
Data Index: 4755457 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.6767. Min Act: -0.1699
Data Index: 1965515 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.6455. Min Act: -0.1700
Data Index: 2700734 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.6142. Min Act: -0.1700
Data Index: 3839023 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.6455. Min Act: -0.1700
Data Index: 8811752 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.6455. Min Act: -0.1700
Data Index: 3245519 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.6455. Min Act: -0.1700
Data Index: 2152858 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.6455. Min Act: -0.1700
Data Index: 1835288 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8955. Min Range: -6.8955
Max Act: 6.6455. Min Act: -0.1700
Data Index: 2700265 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19