Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2551 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3649. Min Range: -6.3649
Max Act: 6.3649. Min Act: -0.1700
Data Index: 3768034 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3649. Min Range: -6.3649
Max Act: 6.2399. Min Act: -0.1700
Data Index: 6856009 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3649. Min Range: -6.3649
Max Act: 6.0524. Min Act: -0.1700
Data Index: 7462895 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3649. Min Range: -6.3649
Max Act: 6.0524. Min Act: -0.1700
Data Index: 6189839 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3649. Min Range: -6.3649
Max Act: 6.0211. Min Act: -0.1700
Data Index: 5212058 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3649. Min Range: -6.3649
Max Act: 5.9274. Min Act: -0.1700
Data Index: 288948 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3649. Min Range: -6.3649
Max Act: 5.8961. Min Act: -0.1700
Data Index: 1371174 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3649. Min Range: -6.3649
Max Act: 5.8961. Min Act: -0.1700
Data Index: 6953203 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3649. Min Range: -6.3649
Max Act: 5.9274. Min Act: -0.1700
Data Index: 8518451 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3649. Min Range: -6.3649
Max Act: 5.8649. Min Act: -0.1700
Data Index: 7198169 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3649. Min Range: -6.3649
Max Act: 5.8336. Min Act: -0.1700
Data Index: 7947650 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3649. Min Range: -6.3649
Max Act: 5.7711. Min Act: -0.1700
Data Index: 8063447 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3649. Min Range: -6.3649
Max Act: 5.7711. Min Act: -0.1700
Data Index: 1504689 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3649. Min Range: -6.3649
Max Act: 5.7086. Min Act: -0.1700
Data Index: 6485240 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3649. Min Range: -6.3649
Max Act: 5.7086. Min Act: -0.1700
Data Index: 4184063 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3649. Min Range: -6.3649
Max Act: 5.6774. Min Act: -0.1700
Data Index: 8453921 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3649. Min Range: -6.3649
Max Act: 5.6774. Min Act: -0.1700
Data Index: 5494938 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3649. Min Range: -6.3649
Max Act: 5.6774. Min Act: -0.1700
Data Index: 6217270 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3649. Min Range: -6.3649
Max Act: 5.6774. Min Act: -0.1700
Data Index: 2786194 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3649. Min Range: -6.3649
Max Act: 5.6774. Min Act: -0.1700
Data Index: 2923340 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19