Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6309 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9749. Min Range: -7.9749
Max Act: 7.9749. Min Act: -0.1700
Data Index: 4856387 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9749. Min Range: -7.9749
Max Act: 7.4749. Min Act: -0.1700
Data Index: 4424246 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9749. Min Range: -7.9749
Max Act: 7.4749. Min Act: -0.1700
Data Index: 2201969 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9749. Min Range: -7.9749
Max Act: 7.2874. Min Act: -0.1700
Data Index: 4885128 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9749. Min Range: -7.9749
Max Act: 7.2249. Min Act: -0.1700
Data Index: 7338147 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9749. Min Range: -7.9749
Max Act: 7.2249. Min Act: -0.1700
Data Index: 276340 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9749. Min Range: -7.9749
Max Act: 7.1311. Min Act: -0.1700
Data Index: 5361848 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9749. Min Range: -7.9749
Max Act: 7.1311. Min Act: -0.1700
Data Index: 8348640 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9749. Min Range: -7.9749
Max Act: 7.0999. Min Act: -0.1700
Data Index: 6898925 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9749. Min Range: -7.9749
Max Act: 7.0686. Min Act: -0.1700
Data Index: 4600288 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9749. Min Range: -7.9749
Max Act: 7.0686. Min Act: -0.1700
Data Index: 6879590 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9749. Min Range: -7.9749
Max Act: 7.0686. Min Act: -0.1700
Data Index: 2632123 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9749. Min Range: -7.9749
Max Act: 7.0374. Min Act: -0.1700
Data Index: 3790196 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9749. Min Range: -7.9749
Max Act: 6.9436. Min Act: -0.1700
Data Index: 5606776 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9749. Min Range: -7.9749
Max Act: 6.9124. Min Act: -0.1700
Data Index: 8062589 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9749. Min Range: -7.9749
Max Act: 6.8811. Min Act: -0.1700
Data Index: 6951627 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9749. Min Range: -7.9749
Max Act: 6.8499. Min Act: -0.1700
Data Index: 7220281 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9749. Min Range: -7.9749
Max Act: 6.8499. Min Act: -0.1700
Data Index: 1474635 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9749. Min Range: -7.9749
Max Act: 6.8186. Min Act: -0.1700
Data Index: 3448698 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9749. Min Range: -7.9749
Max Act: 6.8186. Min Act: -0.1700
Data Index: 2453729 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19