Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4880 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.8828. Min Act: -0.1700
Data Index: 322789 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.8516. Min Act: -0.1700
Data Index: 4868367 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.8828. Min Act: -0.1700
Data Index: 1965356 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.8203. Min Act: -0.1700
Data Index: 7920375 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.7891. Min Act: -0.1700
Data Index: 7811359 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.7891. Min Act: -0.1700
Data Index: 125749 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.7578. Min Act: -0.1700
Data Index: 702308 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.7891. Min Act: -0.1700
Data Index: 4192546 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.7578. Min Act: -0.1700
Data Index: 6906946 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.7578. Min Act: -0.1700
Data Index: 8105734 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.7578. Min Act: -0.1700
Data Index: 4924494 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.7578. Min Act: -0.1700
Data Index: 8565967 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.7266. Min Act: -0.1700
Data Index: 6597480 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.7266. Min Act: -0.1700
Data Index: 8618356 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.7266. Min Act: -0.1700
Data Index: 1425796 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.6953. Min Act: -0.1700
Data Index: 3384246 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.6953. Min Act: -0.1700
Data Index: 8195755 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.6953. Min Act: -0.1700
Data Index: 4276073 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.6953. Min Act: -0.1700
Data Index: 8275329 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8828. Min Range: -5.8828
Max Act: 5.6953. Min Act: -0.1700
Data Index: 718023 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19