Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1551 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.5937. Min Act: -0.1700
Data Index: 4591984 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4687. Min Act: -0.1700
Data Index: 2840760 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4375. Min Act: -0.1700
Data Index: 7053990 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4375. Min Act: -0.1700
Data Index: 159709 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3750. Min Act: -0.1700
Data Index: 8272295 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3125. Min Act: -0.1700
Data Index: 830587 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.2812. Min Act: -0.1700
Data Index: 664312 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.2500. Min Act: -0.1700
Data Index: 1036921 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.1875. Min Act: -0.1700
Data Index: 528976 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.1562. Min Act: -0.1700
Data Index: 8071040 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.1562. Min Act: -0.1700
Data Index: 1036920 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.1250. Min Act: -0.1700
Data Index: 8272294 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.1250. Min Act: -0.1700
Data Index: 3852484 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.1250. Min Act: -0.1700
Data Index: 885764 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.1250. Min Act: -0.1700
Data Index: 4379813 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.1250. Min Act: -0.1700
Data Index: 6407292 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.0937. Min Act: -0.1700
Data Index: 6217362 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.0937. Min Act: -0.1700
Data Index: 5503294 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.0625. Min Act: -0.1700
Data Index: 529081 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.0625. Min Act: -0.1700
Data Index: 2655601 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19