Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1122 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3794. Min Range: -6.3794
Max Act: 6.3794. Min Act: -0.1700
Data Index: 6432843 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3794. Min Range: -6.3794
Max Act: 6.3794. Min Act: -0.1700
Data Index: 4005569 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3794. Min Range: -6.3794
Max Act: 6.2544. Min Act: -0.1700
Data Index: 8562990 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3794. Min Range: -6.3794
Max Act: 6.1919. Min Act: -0.1700
Data Index: 6815221 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3794. Min Range: -6.3794
Max Act: 6.1607. Min Act: -0.1700
Data Index: 5460547 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3794. Min Range: -6.3794
Max Act: 6.1607. Min Act: -0.1700
Data Index: 7666630 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3794. Min Range: -6.3794
Max Act: 6.1294. Min Act: -0.1700
Data Index: 7895887 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3794. Min Range: -6.3794
Max Act: 6.1294. Min Act: -0.1700
Data Index: 2687429 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3794. Min Range: -6.3794
Max Act: 6.0357. Min Act: -0.1700
Data Index: 6174278 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3794. Min Range: -6.3794
Max Act: 5.9419. Min Act: -0.1700
Data Index: 3042144 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3794. Min Range: -6.3794
Max Act: 5.9107. Min Act: -0.1700
Data Index: 4921377 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3794. Min Range: -6.3794
Max Act: 5.9419. Min Act: -0.1700
Data Index: 6305179 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3794. Min Range: -6.3794
Max Act: 5.9419. Min Act: -0.1700
Data Index: 8548752 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3794. Min Range: -6.3794
Max Act: 5.9419. Min Act: -0.1700
Data Index: 6202471 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3794. Min Range: -6.3794
Max Act: 5.9419. Min Act: -0.1700
Data Index: 4581124 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3794. Min Range: -6.3794
Max Act: 5.9419. Min Act: -0.1700
Data Index: 2523760 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3794. Min Range: -6.3794
Max Act: 5.9419. Min Act: -0.1700
Data Index: 1780081 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3794. Min Range: -6.3794
Max Act: 5.9419. Min Act: -0.1700
Data Index: 5499937 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3794. Min Range: -6.3794
Max Act: 5.8794. Min Act: -0.1700
Data Index: 6620821 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3794. Min Range: -6.3794
Max Act: 5.9107. Min Act: -0.1700
Data Index: 5330899 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19