Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1420 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.5841. Min Act: -0.1700
Data Index: 7535367 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.5357. Min Act: -0.1694
Data Index: 6352637 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.4384. Min Act: -0.1700
Data Index: 6977385 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.4058. Min Act: -0.1695
Data Index: 7657364 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.3895. Min Act: -0.1700
Data Index: 7691056 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.3568. Min Act: -0.1699
Data Index: 7183549 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.3731. Min Act: -0.1697
Data Index: 4017315 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.3568. Min Act: -0.1698
Data Index: 2222617 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.3404. Min Act: -0.1700
Data Index: 6737626 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.3404. Min Act: -0.1700
Data Index: 2167757 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.3404. Min Act: -0.1699
Data Index: 2871595 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.3404. Min Act: -0.1697
Data Index: 4569348 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.3404. Min Act: -0.1700
Data Index: 8000003 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.3404. Min Act: -0.1700
Data Index: 2068078 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.3568. Min Act: -0.1697
Data Index: 2289080 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.3076. Min Act: -0.1700
Data Index: 5318333 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.3076. Min Act: -0.1700
Data Index: 3331170 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.3076. Min Act: -0.1700
Data Index: 2655476 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.2911. Min Act: -0.1700
Data Index: 825812 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5841. Min Range: -2.5841
Max Act: 2.3076. Min Act: -0.1700
Data Index: 1035406 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19