Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 752 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2968. Min Range: -6.2968
Max Act: 6.2968. Min Act: -0.1700
Data Index: 6016412 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2968. Min Range: -6.2968
Max Act: 6.1718. Min Act: -0.1700
Data Index: 2656852 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2968. Min Range: -6.2968
Max Act: 6.1406. Min Act: -0.1700
Data Index: 2241002 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2968. Min Range: -6.2968
Max Act: 6.1093. Min Act: -0.1700
Data Index: 2967948 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2968. Min Range: -6.2968
Max Act: 6.0156. Min Act: -0.1700
Data Index: 3870835 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2968. Min Range: -6.2968
Max Act: 6.0156. Min Act: -0.1700
Data Index: 8294237 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2968. Min Range: -6.2968
Max Act: 6.0156. Min Act: -0.1700
Data Index: 7075302 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2968. Min Range: -6.2968
Max Act: 6.0156. Min Act: -0.1700
Data Index: 7927509 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2968. Min Range: -6.2968
Max Act: 6.0156. Min Act: -0.1700
Data Index: 2729166 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2968. Min Range: -6.2968
Max Act: 5.9843. Min Act: -0.1700
Data Index: 6889332 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2968. Min Range: -6.2968
Max Act: 5.9531. Min Act: -0.1700
Data Index: 2239791 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2968. Min Range: -6.2968
Max Act: 5.9531. Min Act: -0.1700
Data Index: 8171712 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2968. Min Range: -6.2968
Max Act: 5.9218. Min Act: -0.1700
Data Index: 2467795 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2968. Min Range: -6.2968
Max Act: 5.8906. Min Act: -0.1700
Data Index: 6383040 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2968. Min Range: -6.2968
Max Act: 5.8906. Min Act: -0.1700
Data Index: 146158 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2968. Min Range: -6.2968
Max Act: 5.8906. Min Act: -0.1700
Data Index: 6549768 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2968. Min Range: -6.2968
Max Act: 5.8906. Min Act: -0.1700
Data Index: 6772777 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2968. Min Range: -6.2968
Max Act: 5.8906. Min Act: -0.1700
Data Index: 3795113 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2968. Min Range: -6.2968
Max Act: 5.8593. Min Act: -0.1700
Data Index: 4129173 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2968. Min Range: -6.2968
Max Act: 5.8593. Min Act: -0.1700
Data Index: 4903742 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19