Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3136 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.5749. Min Act: -0.1700
Data Index: 137451 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.4812. Min Act: -0.1700
Data Index: 199265 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.4187. Min Act: -0.1700
Data Index: 2399083 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.4187. Min Act: -0.1700
Data Index: 5467586 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.4187. Min Act: -0.1700
Data Index: 4779963 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.3874. Min Act: -0.1700
Data Index: 5854592 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.3562. Min Act: -0.1700
Data Index: 7048009 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.3249. Min Act: -0.1700
Data Index: 5125707 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.3249. Min Act: -0.1700
Data Index: 8626343 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.3249. Min Act: -0.1700
Data Index: 852114 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.3249. Min Act: -0.1700
Data Index: 3124950 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.2937. Min Act: -0.1700
Data Index: 2945511 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.2937. Min Act: -0.1700
Data Index: 7784642 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.2937. Min Act: -0.1700
Data Index: 1099561 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.2937. Min Act: -0.1700
Data Index: 6398063 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.2624. Min Act: -0.1700
Data Index: 6875375 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.2624. Min Act: -0.1700
Data Index: 7996544 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.2624. Min Act: -0.1700
Data Index: 5362188 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.2624. Min Act: -0.1700
Data Index: 4074693 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5749. Min Range: -4.5749
Max Act: 4.2624. Min Act: -0.1700
Data Index: 6511086 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19