Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2635 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.4063. Min Act: -0.1700
Data Index: 5365566 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.3279. Min Act: -0.1700
Data Index: 675504 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.2808. Min Act: -0.1700
Data Index: 2134402 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.3122. Min Act: -0.1700
Data Index: 469655 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.2808. Min Act: -0.1700
Data Index: 875593 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.2494. Min Act: -0.1700
Data Index: 2134403 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.2337. Min Act: -0.1700
Data Index: 5813024 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.2337. Min Act: -0.1700
Data Index: 3107270 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.2494. Min Act: -0.1700
Data Index: 8300570 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.2180. Min Act: -0.1700
Data Index: 2134404 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.2022. Min Act: -0.1700
Data Index: 1991495 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.2180. Min Act: -0.1700
Data Index: 6393668 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.2180. Min Act: -0.1700
Data Index: 995716 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.2180. Min Act: -0.1700
Data Index: 7254779 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.1708. Min Act: -0.1700
Data Index: 5775965 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.1708. Min Act: -0.1700
Data Index: 2780209 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.1708. Min Act: -0.1700
Data Index: 788038 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.1708. Min Act: -0.1700
Data Index: 3114776 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.1708. Min Act: -0.1700
Data Index: 3631577 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4063. Min Range: -3.4063
Max Act: 3.1550. Min Act: -0.1700
Data Index: 6302327 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19