Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3607 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.5602. Min Act: -0.1700
Data Index: 5941687 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.4040. Min Act: -0.1700
Data Index: 378854 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.4040. Min Act: -0.1700
Data Index: 6338958 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.3415. Min Act: -0.1700
Data Index: 3212979 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.3415. Min Act: -0.1700
Data Index: 5692904 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.3102. Min Act: -0.1700
Data Index: 6165981 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.2790. Min Act: -0.1700
Data Index: 3005445 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.2790. Min Act: -0.1700
Data Index: 2675091 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.2477. Min Act: -0.1700
Data Index: 2431514 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.2165. Min Act: -0.1700
Data Index: 2060871 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.1852. Min Act: -0.1700
Data Index: 3537642 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.2165. Min Act: -0.1700
Data Index: 8523927 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.2165. Min Act: -0.1700
Data Index: 3842836 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.1540. Min Act: -0.1700
Data Index: 8614294 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.1852. Min Act: -0.1700
Data Index: 2025351 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.1852. Min Act: -0.1700
Data Index: 1629181 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.1852. Min Act: -0.1700
Data Index: 7294898 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.1852. Min Act: -0.1700
Data Index: 1895317 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.1540. Min Act: -0.1700
Data Index: 6192009 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5602. Min Range: -6.5602
Max Act: 6.1852. Min Act: -0.1700
Data Index: 1775524 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19