Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 898 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0782. Min Range: -4.0782
Max Act: 4.0782. Min Act: -0.1700
Data Index: 1306361 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0782. Min Range: -4.0782
Max Act: 4.0470. Min Act: -0.1700
Data Index: 8187095 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0782. Min Range: -4.0782
Max Act: 4.0157. Min Act: -0.1700
Data Index: 8774131 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0782. Min Range: -4.0782
Max Act: 3.9845. Min Act: -0.1700
Data Index: 6217584 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0782. Min Range: -4.0782
Max Act: 4.0157. Min Act: -0.1700
Data Index: 5005173 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0782. Min Range: -4.0782
Max Act: 4.0157. Min Act: -0.1700
Data Index: 2256625 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0782. Min Range: -4.0782
Max Act: 3.9845. Min Act: -0.1700
Data Index: 5530266 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0782. Min Range: -4.0782
Max Act: 4.0157. Min Act: -0.1700
Data Index: 3531617 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0782. Min Range: -4.0782
Max Act: 4.0157. Min Act: -0.1700
Data Index: 5616777 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0782. Min Range: -4.0782
Max Act: 3.9532. Min Act: -0.1700
Data Index: 4352120 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0782. Min Range: -4.0782
Max Act: 3.9845. Min Act: -0.1700
Data Index: 1938101 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0782. Min Range: -4.0782
Max Act: 3.9532. Min Act: -0.1700
Data Index: 228791 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0782. Min Range: -4.0782
Max Act: 3.9219. Min Act: -0.1700
Data Index: 7298128 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0782. Min Range: -4.0782
Max Act: 3.9219. Min Act: -0.1700
Data Index: 5618068 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0782. Min Range: -4.0782
Max Act: 3.9532. Min Act: -0.1700
Data Index: 3583699 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0782. Min Range: -4.0782
Max Act: 3.9532. Min Act: -0.1700
Data Index: 477557 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0782. Min Range: -4.0782
Max Act: 3.9219. Min Act: -0.1700
Data Index: 6797275 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0782. Min Range: -4.0782
Max Act: 3.9219. Min Act: -0.1700
Data Index: 5666031 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0782. Min Range: -4.0782
Max Act: 3.8907. Min Act: -0.1700
Data Index: 5726906 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0782. Min Range: -4.0782
Max Act: 3.8907. Min Act: -0.1700
Data Index: 7130780 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19