Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3261 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1216. Min Range: -7.1216
Max Act: 7.1216. Min Act: -0.1700
Data Index: 5901649 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1216. Min Range: -7.1216
Max Act: 6.9966. Min Act: -0.1700
Data Index: 8486821 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1216. Min Range: -7.1216
Max Act: 6.9654. Min Act: -0.1700
Data Index: 6806138 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1216. Min Range: -7.1216
Max Act: 6.9654. Min Act: -0.1700
Data Index: 6036064 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1216. Min Range: -7.1216
Max Act: 6.9654. Min Act: -0.1700
Data Index: 976416 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1216. Min Range: -7.1216
Max Act: 6.8716. Min Act: -0.1700
Data Index: 2166908 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1216. Min Range: -7.1216
Max Act: 6.8716. Min Act: -0.1700
Data Index: 990937 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1216. Min Range: -7.1216
Max Act: 6.8404. Min Act: -0.1700
Data Index: 5381669 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1216. Min Range: -7.1216
Max Act: 6.8404. Min Act: -0.1700
Data Index: 525297 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1216. Min Range: -7.1216
Max Act: 6.7779. Min Act: -0.1700
Data Index: 4611169 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1216. Min Range: -7.1216
Max Act: 6.7779. Min Act: -0.1700
Data Index: 1406545 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1216. Min Range: -7.1216
Max Act: 6.8091. Min Act: -0.1700
Data Index: 4750703 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1216. Min Range: -7.1216
Max Act: 6.7779. Min Act: -0.1700
Data Index: 1534245 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1216. Min Range: -7.1216
Max Act: 6.7466. Min Act: -0.1700
Data Index: 4800014 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1216. Min Range: -7.1216
Max Act: 6.7466. Min Act: -0.1700
Data Index: 5622967 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1216. Min Range: -7.1216
Max Act: 6.7466. Min Act: -0.1700
Data Index: 7127299 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1216. Min Range: -7.1216
Max Act: 6.7466. Min Act: -0.1700
Data Index: 719923 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1216. Min Range: -7.1216
Max Act: 6.7154. Min Act: -0.1700
Data Index: 5816991 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1216. Min Range: -7.1216
Max Act: 6.7154. Min Act: -0.1700
Data Index: 2532562 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1216. Min Range: -7.1216
Max Act: 6.7154. Min Act: -0.1700
Data Index: 3265024 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19