Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0512. Min Range: -5.0512
Max Act: 5.0512. Min Act: -0.1700
Data Index: 1474856 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0512. Min Range: -5.0512
Max Act: 5.0199. Min Act: -0.1700
Data Index: 8054385 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0512. Min Range: -5.0512
Max Act: 4.9887. Min Act: -0.1700
Data Index: 4378157 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0512. Min Range: -5.0512
Max Act: 4.8949. Min Act: -0.1700
Data Index: 3139486 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0512. Min Range: -5.0512
Max Act: 4.8637. Min Act: -0.1700
Data Index: 6872465 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0512. Min Range: -5.0512
Max Act: 4.8012. Min Act: -0.1700
Data Index: 6202881 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0512. Min Range: -5.0512
Max Act: 4.7699. Min Act: -0.1700
Data Index: 8777262 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0512. Min Range: -5.0512
Max Act: 4.7074. Min Act: -0.1700
Data Index: 7627798 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0512. Min Range: -5.0512
Max Act: 4.7074. Min Act: -0.1700
Data Index: 5211215 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0512. Min Range: -5.0512
Max Act: 4.7074. Min Act: -0.1700
Data Index: 4092002 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0512. Min Range: -5.0512
Max Act: 4.7074. Min Act: -0.1700
Data Index: 6114248 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0512. Min Range: -5.0512
Max Act: 4.7074. Min Act: -0.1700
Data Index: 718598 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0512. Min Range: -5.0512
Max Act: 4.6762. Min Act: -0.1700
Data Index: 5108709 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0512. Min Range: -5.0512
Max Act: 4.6762. Min Act: -0.1700
Data Index: 6805541 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0512. Min Range: -5.0512
Max Act: 4.6762. Min Act: -0.1700
Data Index: 8275963 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0512. Min Range: -5.0512
Max Act: 4.6449. Min Act: -0.1700
Data Index: 8497834 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0512. Min Range: -5.0512
Max Act: 4.6449. Min Act: -0.1700
Data Index: 901740 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0512. Min Range: -5.0512
Max Act: 4.6449. Min Act: -0.1700
Data Index: 5524643 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0512. Min Range: -5.0512
Max Act: 4.5824. Min Act: -0.1700
Data Index: 7725741 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0512. Min Range: -5.0512
Max Act: 4.6137. Min Act: -0.1700
Data Index: 1719367 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19