Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.7279. Min Act: -0.1700
Data Index: 4479727 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.6029. Min Act: -0.1700
Data Index: 560352 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.5717. Min Act: -0.1700
Data Index: 1160715 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.5092. Min Act: -0.1700
Data Index: 6176783 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.4467. Min Act: -0.1700
Data Index: 8481774 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.4467. Min Act: -0.1700
Data Index: 5372462 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.4154. Min Act: -0.1700
Data Index: 4740252 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.3842. Min Act: -0.1700
Data Index: 1114914 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.4154. Min Act: -0.1700
Data Index: 6116451 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.3842. Min Act: -0.1700
Data Index: 4614899 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.3842. Min Act: -0.1700
Data Index: 6164960 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.3529. Min Act: -0.1700
Data Index: 7662604 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.3529. Min Act: -0.1700
Data Index: 3166561 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.3217. Min Act: -0.1700
Data Index: 1844554 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.2904. Min Act: -0.1700
Data Index: 6654685 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.2904. Min Act: -0.1700
Data Index: 8066536 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.2592. Min Act: -0.1700
Data Index: 5558973 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.2592. Min Act: -0.1700
Data Index: 6613751 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.2279. Min Act: -0.1700
Data Index: 3576532 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7279. Min Range: -5.7279
Max Act: 5.2592. Min Act: -0.1700
Data Index: 4922284 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19