Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3440 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.9722. Min Act: -0.1700
Data Index: 6644564 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.4716. Min Act: -0.1700
Data Index: 5327299 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.4403. Min Act: -0.1700
Data Index: 469850 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.4403. Min Act: -0.1700
Data Index: 1804965 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.4089. Min Act: -0.1700
Data Index: 6624865 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.4089. Min Act: -0.1700
Data Index: 8445966 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.4089. Min Act: -0.1700
Data Index: 6444271 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.4089. Min Act: -0.1700
Data Index: 4764687 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.3932. Min Act: -0.1700
Data Index: 4353080 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.3932. Min Act: -0.1700
Data Index: 6538633 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.3776. Min Act: -0.1700
Data Index: 1810596 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.3776. Min Act: -0.1700
Data Index: 5997057 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.3619. Min Act: -0.1700
Data Index: 3165015 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.3619. Min Act: -0.1700
Data Index: 217526 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.3619. Min Act: -0.1700
Data Index: 6395020 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.3619. Min Act: -0.1700
Data Index: 958115 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.3619. Min Act: -0.1700
Data Index: 6222406 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.3462. Min Act: -0.1700
Data Index: 7771451 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.3462. Min Act: -0.1700
Data Index: 2977738 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9722. Min Range: -3.9722
Max Act: 3.3462. Min Act: -0.1700
Data Index: 7928940 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19