Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3036 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0025. Min Range: -4.0025
Max Act: 3.9712. Min Act: -0.1700
Data Index: 6699173 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0025. Min Range: -4.0025
Max Act: 4.0025. Min Act: -0.1700
Data Index: 8139249 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0025. Min Range: -4.0025
Max Act: 3.9400. Min Act: -0.1700
Data Index: 5024102 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0025. Min Range: -4.0025
Max Act: 3.9712. Min Act: -0.1700
Data Index: 2785888 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0025. Min Range: -4.0025
Max Act: 3.9087. Min Act: -0.1700
Data Index: 2911024 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0025. Min Range: -4.0025
Max Act: 3.9087. Min Act: -0.1700
Data Index: 8440409 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0025. Min Range: -4.0025
Max Act: 3.9712. Min Act: -0.1700
Data Index: 2435753 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0025. Min Range: -4.0025
Max Act: 3.9087. Min Act: -0.1700
Data Index: 2399014 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0025. Min Range: -4.0025
Max Act: 3.8774. Min Act: -0.1700
Data Index: 5249336 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0025. Min Range: -4.0025
Max Act: 3.9087. Min Act: -0.1700
Data Index: 8741085 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0025. Min Range: -4.0025
Max Act: 3.8149. Min Act: -0.1700
Data Index: 4355725 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0025. Min Range: -4.0025
Max Act: 3.8462. Min Act: -0.1700
Data Index: 5127079 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0025. Min Range: -4.0025
Max Act: 3.9087. Min Act: -0.1700
Data Index: 4625719 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0025. Min Range: -4.0025
Max Act: 3.7836. Min Act: -0.1700
Data Index: 5285558 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0025. Min Range: -4.0025
Max Act: 3.7523. Min Act: -0.1700
Data Index: 4944484 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0025. Min Range: -4.0025
Max Act: 3.7836. Min Act: -0.1700
Data Index: 1797109 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0025. Min Range: -4.0025
Max Act: 3.8149. Min Act: -0.1700
Data Index: 8144671 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0025. Min Range: -4.0025
Max Act: 3.7211. Min Act: -0.1700
Data Index: 4904781 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0025. Min Range: -4.0025
Max Act: 3.7836. Min Act: -0.1700
Data Index: 7587594 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0025. Min Range: -4.0025
Max Act: 3.7523. Min Act: -0.1700
Data Index: 2464768 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19