Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3585 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.8852. Min Act: -0.1700
Data Index: 4944901 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.9165. Min Act: -0.1700
Data Index: 4276580 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.8852. Min Act: -0.1700
Data Index: 2190710 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.8540. Min Act: -0.1700
Data Index: 3131234 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.8227. Min Act: -0.1700
Data Index: 661046 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.8227. Min Act: -0.1700
Data Index: 987542 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.8071. Min Act: -0.1700
Data Index: 2590886 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.7445. Min Act: -0.1700
Data Index: 3109193 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.7601. Min Act: -0.1700
Data Index: 187115 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.7445. Min Act: -0.1700
Data Index: 2287205 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.7601. Min Act: -0.1700
Data Index: 4065648 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.7289. Min Act: -0.1700
Data Index: 326862 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.7132. Min Act: -0.1700
Data Index: 4372108 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.7289. Min Act: -0.1700
Data Index: 200945 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.7289. Min Act: -0.1700
Data Index: 5198367 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.6976. Min Act: -0.1700
Data Index: 5570107 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.7132. Min Act: -0.1700
Data Index: 5861805 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.6976. Min Act: -0.1700
Data Index: 4130263 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.6819. Min Act: -0.1700
Data Index: 5244661 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9165. Min Range: -3.9165
Max Act: 3.6819. Min Act: -0.1700
Data Index: 4395549 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19