Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 187 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3539. Min Range: -6.3539
Max Act: 6.3539. Min Act: -0.1700
Data Index: 605678 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3539. Min Range: -6.3539
Max Act: 6.3539. Min Act: -0.1700
Data Index: 2189181 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3539. Min Range: -6.3539
Max Act: 6.1977. Min Act: -0.1700
Data Index: 104285 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3539. Min Range: -6.3539
Max Act: 6.1977. Min Act: -0.1700
Data Index: 2175571 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3539. Min Range: -6.3539
Max Act: 6.1977. Min Act: -0.1700
Data Index: 5359732 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3539. Min Range: -6.3539
Max Act: 6.1977. Min Act: -0.1700
Data Index: 5428016 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3539. Min Range: -6.3539
Max Act: 6.1664. Min Act: -0.1700
Data Index: 2429368 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3539. Min Range: -6.3539
Max Act: 6.0102. Min Act: -0.1700
Data Index: 825206 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3539. Min Range: -6.3539
Max Act: 5.8852. Min Act: -0.1700
Data Index: 303792 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3539. Min Range: -6.3539
Max Act: 5.8539. Min Act: -0.1700
Data Index: 6423524 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3539. Min Range: -6.3539
Max Act: 5.8227. Min Act: -0.1700
Data Index: 197986 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3539. Min Range: -6.3539
Max Act: 5.8227. Min Act: -0.1700
Data Index: 2049677 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3539. Min Range: -6.3539
Max Act: 5.8227. Min Act: -0.1700
Data Index: 5781358 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3539. Min Range: -6.3539
Max Act: 5.8227. Min Act: -0.1700
Data Index: 8198857 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3539. Min Range: -6.3539
Max Act: 5.7914. Min Act: -0.1700
Data Index: 3598113 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3539. Min Range: -6.3539
Max Act: 5.7602. Min Act: -0.1700
Data Index: 3947259 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3539. Min Range: -6.3539
Max Act: 5.7602. Min Act: -0.1700
Data Index: 997375 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3539. Min Range: -6.3539
Max Act: 5.7289. Min Act: -0.1700
Data Index: 3534237 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3539. Min Range: -6.3539
Max Act: 5.7289. Min Act: -0.1700
Data Index: 3947260 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3539. Min Range: -6.3539
Max Act: 5.7289. Min Act: -0.1700
Data Index: 4859774 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19