Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2827 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2557. Min Range: -6.2557
Max Act: 6.2557. Min Act: -0.1700
Data Index: 863688 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2557. Min Range: -6.2557
Max Act: 6.1932. Min Act: -0.1700
Data Index: 8539510 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2557. Min Range: -6.2557
Max Act: 6.2244. Min Act: -0.1700
Data Index: 4932002 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2557. Min Range: -6.2557
Max Act: 6.1307. Min Act: -0.1700
Data Index: 4527938 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2557. Min Range: -6.2557
Max Act: 6.0994. Min Act: -0.1700
Data Index: 7152975 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2557. Min Range: -6.2557
Max Act: 6.0994. Min Act: -0.1700
Data Index: 6069879 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2557. Min Range: -6.2557
Max Act: 6.0994. Min Act: -0.1700
Data Index: 5224902 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2557. Min Range: -6.2557
Max Act: 6.0682. Min Act: -0.1700
Data Index: 3407687 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2557. Min Range: -6.2557
Max Act: 6.0369. Min Act: -0.1700
Data Index: 2189718 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2557. Min Range: -6.2557
Max Act: 6.0369. Min Act: -0.1700
Data Index: 2803077 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2557. Min Range: -6.2557
Max Act: 6.0369. Min Act: -0.1700
Data Index: 6069878 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2557. Min Range: -6.2557
Max Act: 6.0057. Min Act: -0.1700
Data Index: 5881872 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2557. Min Range: -6.2557
Max Act: 6.0057. Min Act: -0.1700
Data Index: 6062152 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2557. Min Range: -6.2557
Max Act: 5.9744. Min Act: -0.1700
Data Index: 8270310 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2557. Min Range: -6.2557
Max Act: 5.9432. Min Act: -0.1700
Data Index: 4264578 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2557. Min Range: -6.2557
Max Act: 5.9744. Min Act: -0.1700
Data Index: 5108647 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2557. Min Range: -6.2557
Max Act: 5.9744. Min Act: -0.1700
Data Index: 3468776 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2557. Min Range: -6.2557
Max Act: 5.9744. Min Act: -0.1700
Data Index: 5660801 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2557. Min Range: -6.2557
Max Act: 5.9432. Min Act: -0.1700
Data Index: 7040895 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2557. Min Range: -6.2557
Max Act: 5.9432. Min Act: -0.1700
Data Index: 2199700 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19