Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2592 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6925. Min Range: -5.6925
Max Act: 5.6925. Min Act: -0.1700
Data Index: 8473209 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6925. Min Range: -5.6925
Max Act: 5.3487. Min Act: -0.1700
Data Index: 6315283 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6925. Min Range: -5.6925
Max Act: 5.1925. Min Act: -0.1700
Data Index: 7766578 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6925. Min Range: -5.6925
Max Act: 5.0987. Min Act: -0.1700
Data Index: 7953696 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6925. Min Range: -5.6925
Max Act: 5.0675. Min Act: -0.1700
Data Index: 5644824 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6925. Min Range: -5.6925
Max Act: 5.0675. Min Act: -0.1700
Data Index: 594986 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6925. Min Range: -5.6925
Max Act: 5.0675. Min Act: -0.1700
Data Index: 7766576 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6925. Min Range: -5.6925
Max Act: 5.0362. Min Act: -0.1700
Data Index: 6797567 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6925. Min Range: -5.6925
Max Act: 5.0050. Min Act: -0.1700
Data Index: 7475276 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6925. Min Range: -5.6925
Max Act: 5.0050. Min Act: -0.1700
Data Index: 4352544 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6925. Min Range: -5.6925
Max Act: 4.9737. Min Act: -0.1700
Data Index: 3088226 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6925. Min Range: -5.6925
Max Act: 4.9112. Min Act: -0.1700
Data Index: 8438052 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6925. Min Range: -5.6925
Max Act: 4.9425. Min Act: -0.1700
Data Index: 8053403 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6925. Min Range: -5.6925
Max Act: 4.9112. Min Act: -0.1700
Data Index: 1344103 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6925. Min Range: -5.6925
Max Act: 4.9112. Min Act: -0.1700
Data Index: 7763732 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6925. Min Range: -5.6925
Max Act: 4.9112. Min Act: -0.1700
Data Index: 6525251 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6925. Min Range: -5.6925
Max Act: 4.9112. Min Act: -0.1700
Data Index: 602293 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6925. Min Range: -5.6925
Max Act: 4.9112. Min Act: -0.1700
Data Index: 7911974 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6925. Min Range: -5.6925
Max Act: 4.8800. Min Act: -0.1700
Data Index: 6808876 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6925. Min Range: -5.6925
Max Act: 4.8800. Min Act: -0.1700
Data Index: 5529497 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19