Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2627 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2652. Min Range: -8.2652
Max Act: 8.2652. Min Act: -0.1700
Data Index: 5396497 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2652. Min Range: -8.2652
Max Act: 8.2027. Min Act: -0.1700
Data Index: 4454008 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2652. Min Range: -8.2652
Max Act: 8.2027. Min Act: -0.1700
Data Index: 5709632 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2652. Min Range: -8.2652
Max Act: 8.2027. Min Act: -0.1700
Data Index: 4584043 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2652. Min Range: -8.2652
Max Act: 8.2027. Min Act: -0.1700
Data Index: 4168125 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2652. Min Range: -8.2652
Max Act: 8.1402. Min Act: -0.1700
Data Index: 5709625 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2652. Min Range: -8.2652
Max Act: 8.1090. Min Act: -0.1700
Data Index: 5270192 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2652. Min Range: -8.2652
Max Act: 8.0777. Min Act: -0.1700
Data Index: 1524791 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2652. Min Range: -8.2652
Max Act: 8.0465. Min Act: -0.1700
Data Index: 6954439 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2652. Min Range: -8.2652
Max Act: 8.0152. Min Act: -0.1700
Data Index: 867016 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2652. Min Range: -8.2652
Max Act: 7.9840. Min Act: -0.1700
Data Index: 561802 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2652. Min Range: -8.2652
Max Act: 7.9840. Min Act: -0.1700
Data Index: 6335768 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2652. Min Range: -8.2652
Max Act: 7.9527. Min Act: -0.1700
Data Index: 6664642 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2652. Min Range: -8.2652
Max Act: 7.8902. Min Act: -0.1700
Data Index: 4740120 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2652. Min Range: -8.2652
Max Act: 7.8902. Min Act: -0.1700
Data Index: 75234 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2652. Min Range: -8.2652
Max Act: 7.8902. Min Act: -0.1700
Data Index: 209177 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2652. Min Range: -8.2652
Max Act: 7.9215. Min Act: -0.1700
Data Index: 614302 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2652. Min Range: -8.2652
Max Act: 7.8277. Min Act: -0.1700
Data Index: 8432600 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2652. Min Range: -8.2652
Max Act: 7.8277. Min Act: -0.1700
Data Index: 7285406 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2652. Min Range: -8.2652
Max Act: 7.8590. Min Act: -0.1700
Data Index: 7000429 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19