Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1385 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.9421. Min Act: -0.1700
Data Index: 6897846 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.8946. Min Act: -0.1700
Data Index: 7195421 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.8470. Min Act: -0.1700
Data Index: 8755760 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.8311. Min Act: -0.1700
Data Index: 6897849 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.8470. Min Act: -0.1700
Data Index: 378840 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.8470. Min Act: -0.1700
Data Index: 1194792 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.8470. Min Act: -0.1700
Data Index: 3506532 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.8470. Min Act: -0.1700
Data Index: 7718815 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.8311. Min Act: -0.1700
Data Index: 6380068 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.8151. Min Act: -0.1700
Data Index: 2371519 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.7992. Min Act: -0.1700
Data Index: 2856024 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.7674. Min Act: -0.1700
Data Index: 840219 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.7674. Min Act: -0.1700
Data Index: 8570848 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.7833. Min Act: -0.1700
Data Index: 8615555 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.7674. Min Act: -0.1700
Data Index: 7795908 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.7992. Min Act: -0.1700
Data Index: 4964209 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.7354. Min Act: -0.1700
Data Index: 5330705 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.7514. Min Act: -0.1700
Data Index: 7301887 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.7674. Min Act: -0.1700
Data Index: 7627077 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9421. Min Range: -2.9421
Max Act: 2.7514. Min Act: -0.1700
Data Index: 1730033 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19