Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2818 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4227. Min Range: -7.4227
Max Act: 7.4227. Min Act: -0.1700
Data Index: 6437542 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4227. Min Range: -7.4227
Max Act: 7.3289. Min Act: -0.1700
Data Index: 7796131 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4227. Min Range: -7.4227
Max Act: 7.2977. Min Act: -0.1700
Data Index: 1812606 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4227. Min Range: -7.4227
Max Act: 7.1727. Min Act: -0.1700
Data Index: 7382706 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4227. Min Range: -7.4227
Max Act: 7.1414. Min Act: -0.1700
Data Index: 3540697 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4227. Min Range: -7.4227
Max Act: 6.9539. Min Act: -0.1700
Data Index: 1403107 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4227. Min Range: -7.4227
Max Act: 6.9539. Min Act: -0.1700
Data Index: 3542922 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4227. Min Range: -7.4227
Max Act: 6.9852. Min Act: -0.1700
Data Index: 8204279 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4227. Min Range: -7.4227
Max Act: 6.9852. Min Act: -0.1700
Data Index: 209955 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4227. Min Range: -7.4227
Max Act: 6.9852. Min Act: -0.1700
Data Index: 6058858 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4227. Min Range: -7.4227
Max Act: 6.9852. Min Act: -0.1700
Data Index: 4936331 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4227. Min Range: -7.4227
Max Act: 6.9852. Min Act: -0.1700
Data Index: 6450049 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4227. Min Range: -7.4227
Max Act: 6.9539. Min Act: -0.1700
Data Index: 3493319 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4227. Min Range: -7.4227
Max Act: 6.9227. Min Act: -0.1700
Data Index: 5172963 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4227. Min Range: -7.4227
Max Act: 6.8602. Min Act: -0.1700
Data Index: 4996584 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4227. Min Range: -7.4227
Max Act: 6.8914. Min Act: -0.1700
Data Index: 2963480 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4227. Min Range: -7.4227
Max Act: 6.8914. Min Act: -0.1700
Data Index: 5797910 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4227. Min Range: -7.4227
Max Act: 6.8289. Min Act: -0.1700
Data Index: 2040746 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4227. Min Range: -7.4227
Max Act: 6.7977. Min Act: -0.1700
Data Index: 7335919 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4227. Min Range: -7.4227
Max Act: 6.8602. Min Act: -0.1700
Data Index: 5612201 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19