Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1407 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3950. Min Range: -4.3950
Max Act: 4.3950. Min Act: -0.1700
Data Index: 4753149 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3950. Min Range: -4.3950
Max Act: 4.2075. Min Act: -0.1700
Data Index: 4559039 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3950. Min Range: -4.3950
Max Act: 4.1137. Min Act: -0.1700
Data Index: 358639 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3950. Min Range: -4.3950
Max Act: 4.0512. Min Act: -0.1700
Data Index: 4800760 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3950. Min Range: -4.3950
Max Act: 4.0512. Min Act: -0.1700
Data Index: 7392624 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3950. Min Range: -4.3950
Max Act: 3.9887. Min Act: -0.1700
Data Index: 1900689 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3950. Min Range: -4.3950
Max Act: 3.9574. Min Act: -0.1700
Data Index: 2013486 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3950. Min Range: -4.3950
Max Act: 3.9418. Min Act: -0.1700
Data Index: 4867895 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3950. Min Range: -4.3950
Max Act: 3.9574. Min Act: -0.1700
Data Index: 3945743 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3950. Min Range: -4.3950
Max Act: 3.9574. Min Act: -0.1700
Data Index: 2232625 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3950. Min Range: -4.3950
Max Act: 3.9418. Min Act: -0.1700
Data Index: 1538580 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3950. Min Range: -4.3950
Max Act: 3.9105. Min Act: -0.1700
Data Index: 8105244 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3950. Min Range: -4.3950
Max Act: 3.9105. Min Act: -0.1700
Data Index: 2829259 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3950. Min Range: -4.3950
Max Act: 3.9262. Min Act: -0.1700
Data Index: 3240827 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3950. Min Range: -4.3950
Max Act: 3.9262. Min Act: -0.1700
Data Index: 4784929 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3950. Min Range: -4.3950
Max Act: 3.9262. Min Act: -0.1700
Data Index: 6335441 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3950. Min Range: -4.3950
Max Act: 3.8949. Min Act: -0.1700
Data Index: 2519289 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3950. Min Range: -4.3950
Max Act: 3.8793. Min Act: -0.1700
Data Index: 1377471 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3950. Min Range: -4.3950
Max Act: 3.8793. Min Act: -0.1700
Data Index: 6199563 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3950. Min Range: -4.3950
Max Act: 3.8636. Min Act: -0.1700
Data Index: 7932677 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19