Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1106 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3963. Min Range: -10.3963
Max Act: 10.3963. Min Act: -0.1700
Data Index: 961550 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3963. Min Range: -10.3963
Max Act: 10.2713. Min Act: -0.1700
Data Index: 8340330 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3963. Min Range: -10.3963
Max Act: 10.2088. Min Act: -0.1700
Data Index: 3778114 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3963. Min Range: -10.3963
Max Act: 10.2088. Min Act: -0.1700
Data Index: 4664358 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3963. Min Range: -10.3963
Max Act: 10.1463. Min Act: -0.1700
Data Index: 2061332 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3963. Min Range: -10.3963
Max Act: 10.1463. Min Act: -0.1700
Data Index: 7112236 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3963. Min Range: -10.3963
Max Act: 10.1463. Min Act: -0.1700
Data Index: 697998 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3963. Min Range: -10.3963
Max Act: 10.1463. Min Act: -0.1700
Data Index: 6765318 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3963. Min Range: -10.3963
Max Act: 10.0838. Min Act: -0.1700
Data Index: 5809232 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3963. Min Range: -10.3963
Max Act: 10.0213. Min Act: -0.1700
Data Index: 3370648 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3963. Min Range: -10.3963
Max Act: 10.1463. Min Act: -0.1700
Data Index: 6896821 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3963. Min Range: -10.3963
Max Act: 10.0838. Min Act: -0.1700
Data Index: 8476956 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3963. Min Range: -10.3963
Max Act: 10.0213. Min Act: -0.1700
Data Index: 1961597 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3963. Min Range: -10.3963
Max Act: 9.9588. Min Act: -0.1700
Data Index: 7390696 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3963. Min Range: -10.3963
Max Act: 10.0213. Min Act: -0.1700
Data Index: 1271336 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3963. Min Range: -10.3963
Max Act: 9.9588. Min Act: -0.1700
Data Index: 6036501 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3963. Min Range: -10.3963
Max Act: 9.9588. Min Act: -0.1700
Data Index: 1791309 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3963. Min Range: -10.3963
Max Act: 9.9588. Min Act: -0.1700
Data Index: 5929194 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3963. Min Range: -10.3963
Max Act: 9.8963. Min Act: -0.1700
Data Index: 1983669 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3963. Min Range: -10.3963
Max Act: 9.8963. Min Act: -0.1700
Data Index: 221176 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19