Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3383 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2891. Min Range: -5.2891
Max Act: 5.2891. Min Act: -0.1700
Data Index: 8482377 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2891. Min Range: -5.2891
Max Act: 5.2891. Min Act: -0.1700
Data Index: 8482378 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2891. Min Range: -5.2891
Max Act: 5.1953. Min Act: -0.1700
Data Index: 1976765 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2891. Min Range: -5.2891
Max Act: 4.5703. Min Act: -0.1700
Data Index: 6172053 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2891. Min Range: -5.2891
Max Act: 4.5703. Min Act: -0.1700
Data Index: 5449967 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2891. Min Range: -5.2891
Max Act: 4.5391. Min Act: -0.1700
Data Index: 6430344 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2891. Min Range: -5.2891
Max Act: 4.5391. Min Act: -0.1700
Data Index: 2313595 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2891. Min Range: -5.2891
Max Act: 4.5703. Min Act: -0.1700
Data Index: 1941135 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2891. Min Range: -5.2891
Max Act: 4.5078. Min Act: -0.1700
Data Index: 2671808 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2891. Min Range: -5.2891
Max Act: 4.4766. Min Act: -0.1700
Data Index: 5644887 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2891. Min Range: -5.2891
Max Act: 4.4141. Min Act: -0.1700
Data Index: 8569791 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2891. Min Range: -5.2891
Max Act: 4.4141. Min Act: -0.1700
Data Index: 2671736 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2891. Min Range: -5.2891
Max Act: 4.3516. Min Act: -0.1700
Data Index: 8094498 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2891. Min Range: -5.2891
Max Act: 4.3203. Min Act: -0.1700
Data Index: 5138477 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2891. Min Range: -5.2891
Max Act: 4.2891. Min Act: -0.1700
Data Index: 6390098 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2891. Min Range: -5.2891
Max Act: 4.3203. Min Act: -0.1700
Data Index: 4812440 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2891. Min Range: -5.2891
Max Act: 4.3203. Min Act: -0.1700
Data Index: 8529288 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2891. Min Range: -5.2891
Max Act: 4.2891. Min Act: -0.1700
Data Index: 1236007 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2891. Min Range: -5.2891
Max Act: 4.2578. Min Act: -0.1700
Data Index: 1548324 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2891. Min Range: -5.2891
Max Act: 4.2891. Min Act: -0.1700
Data Index: 6062725 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19