Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5361 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0698. Min Range: -8.0698
Max Act: 8.0698. Min Act: -0.1700
Data Index: 7250277 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0698. Min Range: -8.0698
Max Act: 8.0073. Min Act: -0.1700
Data Index: 6733028 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0698. Min Range: -8.0698
Max Act: 7.9448. Min Act: -0.1700
Data Index: 6555106 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0698. Min Range: -8.0698
Max Act: 7.8511. Min Act: -0.1700
Data Index: 6000468 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0698. Min Range: -8.0698
Max Act: 7.7886. Min Act: -0.1700
Data Index: 3453803 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0698. Min Range: -8.0698
Max Act: 7.6948. Min Act: -0.1700
Data Index: 172785 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0698. Min Range: -8.0698
Max Act: 7.6636. Min Act: -0.1700
Data Index: 8797109 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0698. Min Range: -8.0698
Max Act: 7.6636. Min Act: -0.1700
Data Index: 3590923 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0698. Min Range: -8.0698
Max Act: 7.6323. Min Act: -0.1700
Data Index: 72859 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0698. Min Range: -8.0698
Max Act: 7.6011. Min Act: -0.1700
Data Index: 4967053 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0698. Min Range: -8.0698
Max Act: 7.6011. Min Act: -0.1700
Data Index: 4930098 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0698. Min Range: -8.0698
Max Act: 7.5073. Min Act: -0.1700
Data Index: 3087245 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0698. Min Range: -8.0698
Max Act: 7.5073. Min Act: -0.1700
Data Index: 285634 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0698. Min Range: -8.0698
Max Act: 7.5073. Min Act: -0.1700
Data Index: 5763850 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0698. Min Range: -8.0698
Max Act: 7.4448. Min Act: -0.1700
Data Index: 8513133 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0698. Min Range: -8.0698
Max Act: 7.4761. Min Act: -0.1700
Data Index: 6111141 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0698. Min Range: -8.0698
Max Act: 7.4448. Min Act: -0.1700
Data Index: 5683835 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0698. Min Range: -8.0698
Max Act: 7.3823. Min Act: -0.1700
Data Index: 6990160 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0698. Min Range: -8.0698
Max Act: 7.3511. Min Act: -0.1700
Data Index: 3568514 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0698. Min Range: -8.0698
Max Act: 7.3823. Min Act: -0.1700
Data Index: 7587288 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19