Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1038 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.7923. Min Range: -11.7923
Max Act: 11.7923. Min Act: -0.1700
Data Index: 228424 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.7923. Min Range: -11.7923
Max Act: 11.6048. Min Act: -0.1700
Data Index: 8493902 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.7923. Min Range: -11.7923
Max Act: 11.4798. Min Act: -0.1700
Data Index: 1577907 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.7923. Min Range: -11.7923
Max Act: 11.4798. Min Act: -0.1700
Data Index: 1577904 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.7923. Min Range: -11.7923
Max Act: 11.3548. Min Act: -0.1700
Data Index: 1033457 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.7923. Min Range: -11.7923
Max Act: 11.2298. Min Act: -0.1700
Data Index: 6770166 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.7923. Min Range: -11.7923
Max Act: 11.2923. Min Act: -0.1700
Data Index: 6199232 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.7923. Min Range: -11.7923
Max Act: 11.3548. Min Act: -0.1700
Data Index: 4430941 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.7923. Min Range: -11.7923
Max Act: 11.2298. Min Act: -0.1700
Data Index: 5549955 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.7923. Min Range: -11.7923
Max Act: 11.1673. Min Act: -0.1700
Data Index: 5818097 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.7923. Min Range: -11.7923
Max Act: 10.9173. Min Act: -0.1700
Data Index: 4225286 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.7923. Min Range: -11.7923
Max Act: 10.9798. Min Act: -0.1700
Data Index: 1233112 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.7923. Min Range: -11.7923
Max Act: 10.9173. Min Act: -0.1700
Data Index: 3328753 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.7923. Min Range: -11.7923
Max Act: 10.8548. Min Act: -0.1700
Data Index: 8525845 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.7923. Min Range: -11.7923
Max Act: 10.8548. Min Act: -0.1700
Data Index: 4346786 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.7923. Min Range: -11.7923
Max Act: 10.9798. Min Act: -0.1700
Data Index: 6512378 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.7923. Min Range: -11.7923
Max Act: 10.9173. Min Act: -0.1700
Data Index: 1647766 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.7923. Min Range: -11.7923
Max Act: 10.7923. Min Act: -0.1700
Data Index: 5533158 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.7923. Min Range: -11.7923
Max Act: 10.7923. Min Act: -0.1700
Data Index: 1560085 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.7923. Min Range: -11.7923
Max Act: 10.7298. Min Act: -0.1700
Data Index: 3495025 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19