Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3516 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0390. Min Range: -4.0390
Max Act: 4.0078. Min Act: -0.1700
Data Index: 2515172 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0390. Min Range: -4.0390
Max Act: 4.0390. Min Act: -0.1700
Data Index: 3411106 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0390. Min Range: -4.0390
Max Act: 3.9765. Min Act: -0.1700
Data Index: 6359791 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0390. Min Range: -4.0390
Max Act: 3.9453. Min Act: -0.1700
Data Index: 296842 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0390. Min Range: -4.0390
Max Act: 3.9453. Min Act: -0.1700
Data Index: 8371408 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0390. Min Range: -4.0390
Max Act: 3.9453. Min Act: -0.1700
Data Index: 5774349 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0390. Min Range: -4.0390
Max Act: 3.8827. Min Act: -0.1700
Data Index: 5692768 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0390. Min Range: -4.0390
Max Act: 3.8827. Min Act: -0.1700
Data Index: 5072012 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0390. Min Range: -4.0390
Max Act: 3.8515. Min Act: -0.1700
Data Index: 1698578 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0390. Min Range: -4.0390
Max Act: 3.8202. Min Act: -0.1700
Data Index: 3121360 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0390. Min Range: -4.0390
Max Act: 3.8515. Min Act: -0.1690
Data Index: 6483700 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0390. Min Range: -4.0390
Max Act: 3.8515. Min Act: -0.1700
Data Index: 1602731 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0390. Min Range: -4.0390
Max Act: 3.8515. Min Act: -0.1700
Data Index: 4669327 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0390. Min Range: -4.0390
Max Act: 3.7889. Min Act: -0.1700
Data Index: 6160201 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0390. Min Range: -4.0390
Max Act: 3.7889. Min Act: -0.1700
Data Index: 296841 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0390. Min Range: -4.0390
Max Act: 3.7576. Min Act: -0.1700
Data Index: 4421057 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0390. Min Range: -4.0390
Max Act: 3.7576. Min Act: -0.1699
Data Index: 5692760 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0390. Min Range: -4.0390
Max Act: 3.7576. Min Act: -0.1700
Data Index: 1021478 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0390. Min Range: -4.0390
Max Act: 3.7576. Min Act: -0.1700
Data Index: 1830175 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0390. Min Range: -4.0390
Max Act: 3.7264. Min Act: -0.1700
Data Index: 3999475 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19