Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3535 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6582. Min Range: -6.6582
Max Act: 6.6582. Min Act: -0.1700
Data Index: 5810459 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6582. Min Range: -6.6582
Max Act: 6.0645. Min Act: -0.1700
Data Index: 5891160 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6582. Min Range: -6.6582
Max Act: 6.0332. Min Act: -0.1700
Data Index: 7873820 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6582. Min Range: -6.6582
Max Act: 6.0332. Min Act: -0.1700
Data Index: 1385654 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6582. Min Range: -6.6582
Max Act: 6.0020. Min Act: -0.1700
Data Index: 1614499 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6582. Min Range: -6.6582
Max Act: 6.0020. Min Act: -0.1700
Data Index: 8163462 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6582. Min Range: -6.6582
Max Act: 5.9395. Min Act: -0.1700
Data Index: 1232211 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6582. Min Range: -6.6582
Max Act: 5.9395. Min Act: -0.1700
Data Index: 8349877 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6582. Min Range: -6.6582
Max Act: 5.9082. Min Act: -0.1700
Data Index: 1539908 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6582. Min Range: -6.6582
Max Act: 5.9082. Min Act: -0.1700
Data Index: 1871876 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6582. Min Range: -6.6582
Max Act: 5.9395. Min Act: -0.1700
Data Index: 5064521 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6582. Min Range: -6.6582
Max Act: 5.8770. Min Act: -0.1700
Data Index: 1756248 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6582. Min Range: -6.6582
Max Act: 5.8770. Min Act: -0.1700
Data Index: 8446685 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6582. Min Range: -6.6582
Max Act: 5.8770. Min Act: -0.1700
Data Index: 2837023 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6582. Min Range: -6.6582
Max Act: 5.8457. Min Act: -0.1700
Data Index: 6817448 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6582. Min Range: -6.6582
Max Act: 5.8457. Min Act: -0.1700
Data Index: 2939510 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6582. Min Range: -6.6582
Max Act: 5.8145. Min Act: -0.1700
Data Index: 7508489 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6582. Min Range: -6.6582
Max Act: 5.8457. Min Act: -0.1700
Data Index: 2294790 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6582. Min Range: -6.6582
Max Act: 5.8457. Min Act: -0.1700
Data Index: 6304939 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6582. Min Range: -6.6582
Max Act: 5.8145. Min Act: -0.1700
Data Index: 2597186 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19