Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 580 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.6638. Min Act: -0.1700
Data Index: 3742342 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.6951. Min Act: -0.1700
Data Index: 80148 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.6638. Min Act: -0.1700
Data Index: 5390446 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.6638. Min Act: -0.1700
Data Index: 3917468 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.6326. Min Act: -0.1700
Data Index: 6576157 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.6326. Min Act: -0.1700
Data Index: 8772512 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.6326. Min Act: -0.1700
Data Index: 5032437 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.6326. Min Act: -0.1700
Data Index: 4103739 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.6013. Min Act: -0.1700
Data Index: 5787227 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.6326. Min Act: -0.1700
Data Index: 6576162 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.5701. Min Act: -0.1700
Data Index: 1123960 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.5701. Min Act: -0.1700
Data Index: 7025944 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.5388. Min Act: -0.1700
Data Index: 3299884 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.5388. Min Act: -0.1700
Data Index: 374586 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.5388. Min Act: -0.1700
Data Index: 7447042 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.5388. Min Act: -0.1700
Data Index: 6061984 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.5388. Min Act: -0.1700
Data Index: 5096907 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.5388. Min Act: -0.1700
Data Index: 6414177 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.5076. Min Act: -0.1700
Data Index: 4532475 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6951. Min Range: -6.6951
Max Act: 6.5076. Min Act: -0.1700
Data Index: 6565773 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19