Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 841 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.9588. Min Act: -0.1700
Data Index: 6475465 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.8963. Min Act: -0.1700
Data Index: 6463595 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.8338. Min Act: -0.1700
Data Index: 5238582 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.6463. Min Act: -0.1700
Data Index: 8235606 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.6463. Min Act: -0.1700
Data Index: 6508220 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.5838. Min Act: -0.1700
Data Index: 4761014 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.5838. Min Act: -0.1700
Data Index: 5079379 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.5213. Min Act: -0.1700
Data Index: 3191318 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.5213. Min Act: -0.1700
Data Index: 4567471 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.5213. Min Act: -0.1700
Data Index: 3518483 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.5213. Min Act: -0.1700
Data Index: 7775656 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.4588. Min Act: -0.1700
Data Index: 1275960 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.3963. Min Act: -0.1700
Data Index: 7457317 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.3963. Min Act: -0.1700
Data Index: 7495577 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.3963. Min Act: -0.1700
Data Index: 6387035 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.3963. Min Act: -0.1700
Data Index: 8549594 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.3338. Min Act: -0.1700
Data Index: 6643623 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.3338. Min Act: -0.1700
Data Index: 2125583 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.3338. Min Act: -0.1700
Data Index: 5750847 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9588. Min Range: -9.9588
Max Act: 9.2713. Min Act: -0.1700
Data Index: 14981 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19