Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3752 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.9816. Min Act: -0.1700
Data Index: 2092510 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.8566. Min Act: -0.1700
Data Index: 633159 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.7941. Min Act: -0.1700
Data Index: 4312431 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.7628. Min Act: -0.1700
Data Index: 2782897 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.7003. Min Act: -0.1700
Data Index: 6646808 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.7003. Min Act: -0.1700
Data Index: 1177189 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.7003. Min Act: -0.1700
Data Index: 3490915 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.6691. Min Act: -0.1700
Data Index: 6646818 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.6378. Min Act: -0.1700
Data Index: 7837353 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.6378. Min Act: -0.1700
Data Index: 2019465 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.6378. Min Act: -0.1700
Data Index: 1306826 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.6691. Min Act: -0.1700
Data Index: 8077904 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.6066. Min Act: -0.1700
Data Index: 3055809 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.5753. Min Act: -0.1700
Data Index: 4221286 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.6066. Min Act: -0.1700
Data Index: 6646815 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.5753. Min Act: -0.1700
Data Index: 2517926 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.5441. Min Act: -0.1700
Data Index: 597691 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.5441. Min Act: -0.1700
Data Index: 6431856 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.5128. Min Act: -0.1700
Data Index: 147210 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9816. Min Range: -5.9816
Max Act: 5.4816. Min Act: -0.1700
Data Index: 45075 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19