Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2581 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.7636. Min Act: -0.1700
Data Index: 1306456 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.6386. Min Act: -0.1700
Data Index: 3520912 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.5761. Min Act: -0.1700
Data Index: 5871206 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.6073. Min Act: -0.1700
Data Index: 7678114 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.5761. Min Act: -0.1700
Data Index: 3520911 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.5136. Min Act: -0.1700
Data Index: 5940401 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.4823. Min Act: -0.1700
Data Index: 3105706 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.4823. Min Act: -0.1700
Data Index: 5675737 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.4823. Min Act: -0.1700
Data Index: 2470359 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.4511. Min Act: -0.1700
Data Index: 7494163 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.4198. Min Act: -0.1700
Data Index: 8765957 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.3886. Min Act: -0.1700
Data Index: 2928346 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.3886. Min Act: -0.1700
Data Index: 2060136 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.3886. Min Act: -0.1700
Data Index: 7156915 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.3261. Min Act: -0.1700
Data Index: 2972918 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.3573. Min Act: -0.1700
Data Index: 4259777 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.3573. Min Act: -0.1700
Data Index: 5167621 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.3261. Min Act: -0.1700
Data Index: 6376119 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.3573. Min Act: -0.1700
Data Index: 8422098 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7636. Min Range: -5.7636
Max Act: 5.3573. Min Act: -0.1700
Data Index: 3079724 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19