Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3220 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5136. Min Range: -10.5136
Max Act: 10.5136. Min Act: -0.1700
Data Index: 5701360 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5136. Min Range: -10.5136
Max Act: 9.7011. Min Act: -0.1700
Data Index: 1875959 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5136. Min Range: -10.5136
Max Act: 9.7011. Min Act: -0.1700
Data Index: 6121796 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5136. Min Range: -10.5136
Max Act: 9.6386. Min Act: -0.1700
Data Index: 7337307 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5136. Min Range: -10.5136
Max Act: 9.6386. Min Act: -0.1700
Data Index: 5420822 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5136. Min Range: -10.5136
Max Act: 9.5761. Min Act: -0.1700
Data Index: 7143113 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5136. Min Range: -10.5136
Max Act: 9.5136. Min Act: -0.1700
Data Index: 2759933 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5136. Min Range: -10.5136
Max Act: 9.4511. Min Act: -0.1700
Data Index: 6246495 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5136. Min Range: -10.5136
Max Act: 9.4511. Min Act: -0.1700
Data Index: 5091082 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5136. Min Range: -10.5136
Max Act: 9.4511. Min Act: -0.1700
Data Index: 1021236 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5136. Min Range: -10.5136
Max Act: 9.3886. Min Act: -0.1697
Data Index: 5685526 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5136. Min Range: -10.5136
Max Act: 9.3261. Min Act: -0.1700
Data Index: 1850060 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5136. Min Range: -10.5136
Max Act: 9.3261. Min Act: -0.1700
Data Index: 1007163 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5136. Min Range: -10.5136
Max Act: 9.2636. Min Act: -0.1700
Data Index: 2020433 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5136. Min Range: -10.5136
Max Act: 9.2636. Min Act: -0.1700
Data Index: 4323679 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5136. Min Range: -10.5136
Max Act: 9.2011. Min Act: -0.1700
Data Index: 8199418 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5136. Min Range: -10.5136
Max Act: 9.2011. Min Act: -0.1700
Data Index: 3053682 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5136. Min Range: -10.5136
Max Act: 9.2011. Min Act: -0.1700
Data Index: 3848430 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5136. Min Range: -10.5136
Max Act: 9.2011. Min Act: -0.1700
Data Index: 3332700 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5136. Min Range: -10.5136
Max Act: 9.2011. Min Act: -0.1700
Data Index: 4895854 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19