Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2714 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.7113. Min Act: -0.1700
Data Index: 8832179 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.6800. Min Act: -0.1700
Data Index: 1802898 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.7113. Min Act: -0.1700
Data Index: 1802890 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.6488. Min Act: -0.1700
Data Index: 4655060 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.5863. Min Act: -0.1700
Data Index: 5230655 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.4613. Min Act: -0.1700
Data Index: 7484303 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.4613. Min Act: -0.1700
Data Index: 1784010 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.4300. Min Act: -0.1700
Data Index: 4189565 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.3675. Min Act: -0.1700
Data Index: 210153 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.3988. Min Act: -0.1700
Data Index: 3534652 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.3988. Min Act: -0.1700
Data Index: 66961 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.3675. Min Act: -0.1700
Data Index: 7666538 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.3363. Min Act: -0.1700
Data Index: 8044385 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.3363. Min Act: -0.1700
Data Index: 2581700 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.3050. Min Act: -0.1700
Data Index: 3305015 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.2738. Min Act: -0.1700
Data Index: 8696872 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.3050. Min Act: -0.1700
Data Index: 4507462 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.3050. Min Act: -0.1700
Data Index: 8264171 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.3050. Min Act: -0.1700
Data Index: 3958126 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7113. Min Range: -5.7113
Max Act: 5.3050. Min Act: -0.1700
Data Index: 7348247 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19