Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4263 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.6552. Min Act: -0.1700
Data Index: 2600968 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.6239. Min Act: -0.1700
Data Index: 6450603 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.5613. Min Act: -0.1700
Data Index: 6712027 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.5143. Min Act: -0.1700
Data Index: 106694 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.5143. Min Act: -0.1700
Data Index: 2941142 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.5143. Min Act: -0.1700
Data Index: 8110841 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.5143. Min Act: -0.1700
Data Index: 5446762 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.4987. Min Act: -0.1700
Data Index: 2690599 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.5143. Min Act: -0.1700
Data Index: 5200074 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.4830. Min Act: -0.1700
Data Index: 1660445 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.4987. Min Act: -0.1700
Data Index: 8313208 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.4830. Min Act: -0.1700
Data Index: 6050550 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.4674. Min Act: -0.1700
Data Index: 3484681 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.4674. Min Act: -0.1700
Data Index: 235075 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.4360. Min Act: -0.1700
Data Index: 7694892 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.4360. Min Act: -0.1700
Data Index: 3816675 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.4517. Min Act: -0.1700
Data Index: 5398383 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.4360. Min Act: -0.1700
Data Index: 5820390 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.4360. Min Act: -0.1700
Data Index: 3777827 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6552. Min Range: -3.6552
Max Act: 3.4517. Min Act: -0.1700
Data Index: 6241446 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19