Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3786 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.5691. Min Act: -0.1700
Data Index: 8792600 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.5691. Min Act: -0.1700
Data Index: 8255977 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.5066. Min Act: -0.1700
Data Index: 832607 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.3816. Min Act: -0.1700
Data Index: 292158 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.3191. Min Act: -0.1700
Data Index: 875962 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.3191. Min Act: -0.1700
Data Index: 7280073 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.2879. Min Act: -0.1700
Data Index: 3574954 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.3191. Min Act: -0.1700
Data Index: 3356078 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.2254. Min Act: -0.1700
Data Index: 3898630 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.2566. Min Act: -0.1700
Data Index: 2219074 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.2254. Min Act: -0.1700
Data Index: 2394161 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.2254. Min Act: -0.1700
Data Index: 7032639 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.2254. Min Act: -0.1700
Data Index: 769954 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.1941. Min Act: -0.1700
Data Index: 3836768 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.1941. Min Act: -0.1700
Data Index: 5011542 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.1941. Min Act: -0.1700
Data Index: 7717168 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.1629. Min Act: -0.1700
Data Index: 4257926 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.1629. Min Act: -0.1700
Data Index: 2201792 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.1316. Min Act: -0.1700
Data Index: 5445204 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5691. Min Range: -6.5691
Max Act: 6.1004. Min Act: -0.1700
Data Index: 2614945 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19