Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2400 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7888. Min Range: -8.7888
Max Act: 8.7888. Min Act: -0.1700
Data Index: 374137 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7888. Min Range: -8.7888
Max Act: 8.2263. Min Act: -0.1700
Data Index: 7541127 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7888. Min Range: -8.7888
Max Act: 8.1013. Min Act: -0.1700
Data Index: 3307824 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7888. Min Range: -8.7888
Max Act: 8.0388. Min Act: -0.1700
Data Index: 2241101 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7888. Min Range: -8.7888
Max Act: 8.0076. Min Act: -0.1700
Data Index: 6971562 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7888. Min Range: -8.7888
Max Act: 8.0076. Min Act: -0.1700
Data Index: 6809221 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7888. Min Range: -8.7888
Max Act: 7.8513. Min Act: -0.1700
Data Index: 8267939 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7888. Min Range: -8.7888
Max Act: 7.7888. Min Act: -0.1700
Data Index: 5707925 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7888. Min Range: -8.7888
Max Act: 7.7576. Min Act: -0.1700
Data Index: 3303472 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7888. Min Range: -8.7888
Max Act: 7.7263. Min Act: -0.1700
Data Index: 4196683 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7888. Min Range: -8.7888
Max Act: 7.7576. Min Act: -0.1700
Data Index: 8409784 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7888. Min Range: -8.7888
Max Act: 7.7263. Min Act: -0.1700
Data Index: 3674454 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7888. Min Range: -8.7888
Max Act: 7.6951. Min Act: -0.1700
Data Index: 259737 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7888. Min Range: -8.7888
Max Act: 7.6638. Min Act: -0.1700
Data Index: 477429 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7888. Min Range: -8.7888
Max Act: 7.6638. Min Act: -0.1700
Data Index: 2063178 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7888. Min Range: -8.7888
Max Act: 7.6326. Min Act: -0.1700
Data Index: 3548896 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7888. Min Range: -8.7888
Max Act: 7.6638. Min Act: -0.1700
Data Index: 986067 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7888. Min Range: -8.7888
Max Act: 7.6326. Min Act: -0.1700
Data Index: 2900123 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7888. Min Range: -8.7888
Max Act: 7.6326. Min Act: -0.1700
Data Index: 1422070 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7888. Min Range: -8.7888
Max Act: 7.6326. Min Act: -0.1700
Data Index: 2668109 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19