Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3596 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.2666. Min Act: -0.1700
Data Index: 4009860 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.2354. Min Act: -0.1700
Data Index: 7093683 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.2666. Min Act: -0.1700
Data Index: 1335948 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.1729. Min Act: -0.1700
Data Index: 1114776 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.1416. Min Act: -0.1700
Data Index: 8554946 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.1729. Min Act: -0.1700
Data Index: 3495986 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.1416. Min Act: -0.1700
Data Index: 2454862 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.1416. Min Act: -0.1700
Data Index: 451588 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.1416. Min Act: -0.1700
Data Index: 6778700 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.1104. Min Act: -0.1700
Data Index: 2784005 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.1416. Min Act: -0.1700
Data Index: 7145412 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.1416. Min Act: -0.1700
Data Index: 386457 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.1416. Min Act: -0.1700
Data Index: 4551655 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.1416. Min Act: -0.1700
Data Index: 1088777 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.1104. Min Act: -0.1700
Data Index: 407639 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.1104. Min Act: -0.1700
Data Index: 8458161 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.1104. Min Act: -0.1700
Data Index: 601398 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.0791. Min Act: -0.1700
Data Index: 4468478 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.0791. Min Act: -0.1700
Data Index: 2627015 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2666. Min Range: -4.2666
Max Act: 4.0791. Min Act: -0.1700
Data Index: 1983170 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19