Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3546 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.7139. Min Act: -0.1700
Data Index: 8269751 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.5889. Min Act: -0.1700
Data Index: 5799610 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.5576. Min Act: -0.1700
Data Index: 2710765 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.5576. Min Act: -0.1700
Data Index: 1500270 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.5264. Min Act: -0.1700
Data Index: 2686777 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.5264. Min Act: -0.1700
Data Index: 1739782 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.4951. Min Act: -0.1700
Data Index: 6911748 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.4951. Min Act: -0.1700
Data Index: 565544 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.4639. Min Act: -0.1700
Data Index: 7589360 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.4951. Min Act: -0.1700
Data Index: 3690564 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.4326. Min Act: -0.1700
Data Index: 3218442 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.4014. Min Act: -0.1700
Data Index: 1814848 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.4326. Min Act: -0.1700
Data Index: 3164940 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.4014. Min Act: -0.1700
Data Index: 3018307 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.4014. Min Act: -0.1700
Data Index: 6633373 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.3701. Min Act: -0.1700
Data Index: 8767196 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.3389. Min Act: -0.1700
Data Index: 8417855 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.3701. Min Act: -0.1700
Data Index: 2006794 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.3701. Min Act: -0.1700
Data Index: 2618181 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7139. Min Range: -5.7139
Max Act: 5.3701. Min Act: -0.1700
Data Index: 5990077 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19