Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3656 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2890. Min Range: -5.2890
Max Act: 5.2890. Min Act: -0.1700
Data Index: 4586609 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2890. Min Range: -5.2890
Max Act: 5.1640. Min Act: -0.1700
Data Index: 7282720 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2890. Min Range: -5.2890
Max Act: 5.0390. Min Act: -0.1700
Data Index: 4666053 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2890. Min Range: -5.2890
Max Act: 5.0390. Min Act: -0.1700
Data Index: 7225718 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2890. Min Range: -5.2890
Max Act: 5.0390. Min Act: -0.1700
Data Index: 1565906 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2890. Min Range: -5.2890
Max Act: 4.9765. Min Act: -0.1700
Data Index: 1670727 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2890. Min Range: -5.2890
Max Act: 4.9765. Min Act: -0.1700
Data Index: 2855955 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2890. Min Range: -5.2890
Max Act: 4.9453. Min Act: -0.1700
Data Index: 7803604 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2890. Min Range: -5.2890
Max Act: 4.9140. Min Act: -0.1700
Data Index: 5657577 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2890. Min Range: -5.2890
Max Act: 4.9140. Min Act: -0.1700
Data Index: 7896928 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2890. Min Range: -5.2890
Max Act: 4.9453. Min Act: -0.1700
Data Index: 1091620 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2890. Min Range: -5.2890
Max Act: 4.8828. Min Act: -0.1700
Data Index: 4829111 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2890. Min Range: -5.2890
Max Act: 4.8828. Min Act: -0.1700
Data Index: 2068929 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2890. Min Range: -5.2890
Max Act: 4.8515. Min Act: -0.1700
Data Index: 1786215 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2890. Min Range: -5.2890
Max Act: 4.8203. Min Act: -0.1700
Data Index: 2499784 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2890. Min Range: -5.2890
Max Act: 4.7890. Min Act: -0.1700
Data Index: 3361076 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2890. Min Range: -5.2890
Max Act: 4.7890. Min Act: -0.1700
Data Index: 5551528 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2890. Min Range: -5.2890
Max Act: 4.7890. Min Act: -0.1700
Data Index: 5104239 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2890. Min Range: -5.2890
Max Act: 4.7890. Min Act: -0.1700
Data Index: 7344816 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2890. Min Range: -5.2890
Max Act: 4.7578. Min Act: -0.1700
Data Index: 2661105 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19