Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3519 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0198. Min Range: -6.0198
Max Act: 6.0198. Min Act: -0.1700
Data Index: 90396 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.9260. Min Act: -0.1700
Data Index: 4758348 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.7073. Min Act: -0.1700
Data Index: 7719793 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.7073. Min Act: -0.1700
Data Index: 8068625 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.6760. Min Act: -0.1700
Data Index: 4411392 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.6760. Min Act: -0.1700
Data Index: 3475232 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.6760. Min Act: -0.1700
Data Index: 1110912 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.6760. Min Act: -0.1700
Data Index: 5560693 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.6135. Min Act: -0.1700
Data Index: 933892 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.6448. Min Act: -0.1700
Data Index: 2117068 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.6135. Min Act: -0.1700
Data Index: 6765729 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.6135. Min Act: -0.1700
Data Index: 6275703 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.6135. Min Act: -0.1700
Data Index: 1609571 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.6135. Min Act: -0.1700
Data Index: 7757938 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.6135. Min Act: -0.1700
Data Index: 4595936 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.6135. Min Act: -0.1700
Data Index: 7820157 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.5823. Min Act: -0.1700
Data Index: 6581903 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.5823. Min Act: -0.1700
Data Index: 6524979 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.5510. Min Act: -0.1700
Data Index: 7233518 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.5823. Min Act: -0.1700
Data Index: 515681 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19