Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.8710. Min Act: -0.1700
Data Index: 2801935 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.8085. Min Act: -0.1700
Data Index: 8070873 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.7772. Min Act: -0.1700
Data Index: 4063257 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.7460. Min Act: -0.1700
Data Index: 1905588 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.7460. Min Act: -0.1700
Data Index: 1786599 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.7147. Min Act: -0.1700
Data Index: 2048737 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.7147. Min Act: -0.1700
Data Index: 6010503 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.6835. Min Act: -0.1700
Data Index: 4214572 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.6835. Min Act: -0.1700
Data Index: 1839406 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.6835. Min Act: -0.1700
Data Index: 8080850 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.6210. Min Act: -0.1700
Data Index: 4908115 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.5897. Min Act: -0.1700
Data Index: 3819178 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.6210. Min Act: -0.1700
Data Index: 2386456 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.6210. Min Act: -0.1700
Data Index: 7870757 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.6210. Min Act: -0.1700
Data Index: 8223959 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.6210. Min Act: -0.1700
Data Index: 359849 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.5585. Min Act: -0.1700
Data Index: 3096366 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.5585. Min Act: -0.1700
Data Index: 2071709 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.5897. Min Act: -0.1700
Data Index: 5263008 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8710. Min Range: -5.8710
Max Act: 5.5585. Min Act: -0.1700
Data Index: 1322876 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19