Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2147 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.8600. Min Act: -0.1700
Data Index: 3773067 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.6412. Min Act: -0.1700
Data Index: 6701209 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.6412. Min Act: -0.1700
Data Index: 5207106 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.3912. Min Act: -0.1700
Data Index: 7840151 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.3600. Min Act: -0.1700
Data Index: 5803298 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.3287. Min Act: -0.1700
Data Index: 4163167 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.3287. Min Act: -0.1700
Data Index: 747124 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.3287. Min Act: -0.1700
Data Index: 3057879 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.2662. Min Act: -0.1700
Data Index: 575350 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.2662. Min Act: -0.1700
Data Index: 5539495 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.2662. Min Act: -0.1700
Data Index: 4256039 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.2350. Min Act: -0.1700
Data Index: 3684168 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.2350. Min Act: -0.1700
Data Index: 2442870 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.2037. Min Act: -0.1700
Data Index: 6422138 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.1725. Min Act: -0.1700
Data Index: 6228103 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.1725. Min Act: -0.1700
Data Index: 3536720 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.1100. Min Act: -0.1700
Data Index: 261043 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.0787. Min Act: -0.1700
Data Index: 7298820 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.0787. Min Act: -0.1700
Data Index: 8513745 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8600. Min Range: -6.8600
Max Act: 6.0787. Min Act: -0.1700
Data Index: 460666 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19