Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4639 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0672. Min Range: -8.0672
Max Act: 8.0672. Min Act: -0.1700
Data Index: 8729110 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0672. Min Range: -8.0672
Max Act: 8.0672. Min Act: -0.1700
Data Index: 911122 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0672. Min Range: -8.0672
Max Act: 7.9422. Min Act: -0.1700
Data Index: 7538741 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0672. Min Range: -8.0672
Max Act: 8.0047. Min Act: -0.1700
Data Index: 7433775 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0672. Min Range: -8.0672
Max Act: 7.9422. Min Act: -0.1700
Data Index: 3204816 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0672. Min Range: -8.0672
Max Act: 7.9422. Min Act: -0.1700
Data Index: 2420832 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0672. Min Range: -8.0672
Max Act: 7.9422. Min Act: -0.1700
Data Index: 2036922 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0672. Min Range: -8.0672
Max Act: 7.8797. Min Act: -0.1700
Data Index: 136247 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0672. Min Range: -8.0672
Max Act: 7.9422. Min Act: -0.1700
Data Index: 5103356 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0672. Min Range: -8.0672
Max Act: 7.8172. Min Act: -0.1700
Data Index: 3728407 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0672. Min Range: -8.0672
Max Act: 7.8172. Min Act: -0.1700
Data Index: 4273911 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0672. Min Range: -8.0672
Max Act: 7.8172. Min Act: -0.1700
Data Index: 1086485 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0672. Min Range: -8.0672
Max Act: 7.8172. Min Act: -0.1700
Data Index: 7227300 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0672. Min Range: -8.0672
Max Act: 7.7547. Min Act: -0.1700
Data Index: 1815731 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0672. Min Range: -8.0672
Max Act: 7.6922. Min Act: -0.1700
Data Index: 2572791 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0672. Min Range: -8.0672
Max Act: 7.7547. Min Act: -0.1700
Data Index: 1093281 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0672. Min Range: -8.0672
Max Act: 7.7547. Min Act: -0.1700
Data Index: 2594145 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0672. Min Range: -8.0672
Max Act: 7.7547. Min Act: -0.1700
Data Index: 1917655 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0672. Min Range: -8.0672
Max Act: 7.7547. Min Act: -0.1700
Data Index: 2933359 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0672. Min Range: -8.0672
Max Act: 7.7547. Min Act: -0.1700
Data Index: 7228926 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19