Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3814 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.5791. Min Act: -0.1700
Data Index: 6693801 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.4854. Min Act: -0.1700
Data Index: 7664983 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.4229. Min Act: -0.1700
Data Index: 3820329 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.4229. Min Act: -0.1700
Data Index: 5032085 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.4229. Min Act: -0.1700
Data Index: 443235 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.3291. Min Act: -0.1700
Data Index: 3985012 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.3291. Min Act: -0.1700
Data Index: 7008034 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.3291. Min Act: -0.1700
Data Index: 7704763 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.2979. Min Act: -0.1700
Data Index: 2109501 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.2666. Min Act: -0.1700
Data Index: 5198566 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.2354. Min Act: -0.1700
Data Index: 6084667 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.2354. Min Act: -0.1700
Data Index: 1686066 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.2041. Min Act: -0.1700
Data Index: 5126132 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.2041. Min Act: -0.1700
Data Index: 1177532 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.2354. Min Act: -0.1700
Data Index: 1946892 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.1729. Min Act: -0.1700
Data Index: 4446622 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.1729. Min Act: -0.1700
Data Index: 8792329 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.1416. Min Act: -0.1700
Data Index: 6029373 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.1104. Min Act: -0.1700
Data Index: 3323781 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5791. Min Range: -5.5791
Max Act: 5.0791. Min Act: -0.1700
Data Index: 3737072 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19