Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0918. Min Range: -5.0918
Max Act: 5.0918. Min Act: -0.1700
Data Index: 6119103 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0918. Min Range: -5.0918
Max Act: 5.0918. Min Act: -0.1700
Data Index: 5330369 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0918. Min Range: -5.0918
Max Act: 5.0293. Min Act: -0.1700
Data Index: 6432455 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0918. Min Range: -5.0918
Max Act: 5.0605. Min Act: -0.1700
Data Index: 5607425 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0918. Min Range: -5.0918
Max Act: 4.9980. Min Act: -0.1700
Data Index: 5418174 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0918. Min Range: -5.0918
Max Act: 4.9668. Min Act: -0.1700
Data Index: 8104831 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0918. Min Range: -5.0918
Max Act: 4.9043. Min Act: -0.1700
Data Index: 8564225 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0918. Min Range: -5.0918
Max Act: 4.9043. Min Act: -0.1700
Data Index: 8359018 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0918. Min Range: -5.0918
Max Act: 4.9355. Min Act: -0.1700
Data Index: 169889 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0918. Min Range: -5.0918
Max Act: 4.9043. Min Act: -0.1700
Data Index: 6479152 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0918. Min Range: -5.0918
Max Act: 4.8730. Min Act: -0.1700
Data Index: 2340758 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0918. Min Range: -5.0918
Max Act: 4.8418. Min Act: -0.1700
Data Index: 7277550 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0918. Min Range: -5.0918
Max Act: 4.8418. Min Act: -0.1700
Data Index: 1199106 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0918. Min Range: -5.0918
Max Act: 4.8418. Min Act: -0.1700
Data Index: 372055 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0918. Min Range: -5.0918
Max Act: 4.8105. Min Act: -0.1700
Data Index: 4164206 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0918. Min Range: -5.0918
Max Act: 4.8105. Min Act: -0.1700
Data Index: 1411419 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0918. Min Range: -5.0918
Max Act: 4.8105. Min Act: -0.1700
Data Index: 930254 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0918. Min Range: -5.0918
Max Act: 4.7793. Min Act: -0.1700
Data Index: 8119818 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0918. Min Range: -5.0918
Max Act: 4.7793. Min Act: -0.1700
Data Index: 5452940 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0918. Min Range: -5.0918
Max Act: 4.7793. Min Act: -0.1700
Data Index: 8424864 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19