Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 516 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.6830. Min Act: -0.1700
Data Index: 1648780 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.5893. Min Act: -0.1700
Data Index: 1505562 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.5893. Min Act: -0.1700
Data Index: 4328783 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4955. Min Act: -0.1700
Data Index: 7514603 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4330. Min Act: -0.1700
Data Index: 2621691 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4330. Min Act: -0.1700
Data Index: 2990702 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4018. Min Act: -0.1700
Data Index: 1904408 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3705. Min Act: -0.1700
Data Index: 4958273 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3705. Min Act: -0.1700
Data Index: 5154575 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3393. Min Act: -0.1700
Data Index: 7229925 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3393. Min Act: -0.1700
Data Index: 4502212 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3393. Min Act: -0.1700
Data Index: 7717904 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3080. Min Act: -0.1700
Data Index: 7942543 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3080. Min Act: -0.1700
Data Index: 6784208 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3080. Min Act: -0.1700
Data Index: 3425197 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3080. Min Act: -0.1700
Data Index: 4796304 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.2768. Min Act: -0.1700
Data Index: 3105840 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3080. Min Act: -0.1700
Data Index: 1598875 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.2768. Min Act: -0.1700
Data Index: 1118725 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.2768. Min Act: -0.1700
Data Index: 6568748 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19