Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2767 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.4808. Min Act: -0.1700
Data Index: 5413661 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.3870. Min Act: -0.1700
Data Index: 417637 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.3558. Min Act: -0.1700
Data Index: 1158300 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.2620. Min Act: -0.1700
Data Index: 1019678 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.2620. Min Act: -0.1700
Data Index: 8294383 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.2620. Min Act: -0.1700
Data Index: 1362911 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.2933. Min Act: -0.1700
Data Index: 8604360 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.2620. Min Act: -0.1700
Data Index: 5338175 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.2620. Min Act: -0.1700
Data Index: 7770091 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.1995. Min Act: -0.1700
Data Index: 3356917 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.1995. Min Act: -0.1700
Data Index: 5028958 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.1683. Min Act: -0.1700
Data Index: 3073566 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.2308. Min Act: -0.1700
Data Index: 6627366 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.1370. Min Act: -0.1700
Data Index: 3576124 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.1683. Min Act: -0.1700
Data Index: 450935 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.1995. Min Act: -0.1700
Data Index: 6679466 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.1683. Min Act: -0.1700
Data Index: 5849829 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.1995. Min Act: -0.1700
Data Index: 8434656 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.1370. Min Act: -0.1700
Data Index: 4989403 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4808. Min Range: -6.4808
Max Act: 6.1058. Min Act: -0.1700
Data Index: 5021607 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19