Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2340 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3306. Min Range: -8.3306
Max Act: 8.3306. Min Act: -0.1700
Data Index: 3858086 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3306. Min Range: -8.3306
Max Act: 8.2056. Min Act: -0.1700
Data Index: 2324038 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3306. Min Range: -8.3306
Max Act: 7.7056. Min Act: -0.1700
Data Index: 5391088 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3306. Min Range: -8.3306
Max Act: 7.6431. Min Act: -0.1700
Data Index: 8666496 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3306. Min Range: -8.3306
Max Act: 7.5806. Min Act: -0.1700
Data Index: 7066305 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3306. Min Range: -8.3306
Max Act: 7.5806. Min Act: -0.1700
Data Index: 7714910 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3306. Min Range: -8.3306
Max Act: 7.5806. Min Act: -0.1700
Data Index: 5158855 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3306. Min Range: -8.3306
Max Act: 7.5806. Min Act: -0.1700
Data Index: 5462119 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3306. Min Range: -8.3306
Max Act: 7.5806. Min Act: -0.1700
Data Index: 3567553 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3306. Min Range: -8.3306
Max Act: 7.5181. Min Act: -0.1700
Data Index: 1801919 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3306. Min Range: -8.3306
Max Act: 7.5181. Min Act: -0.1700
Data Index: 4394422 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3306. Min Range: -8.3306
Max Act: 7.5181. Min Act: -0.1700
Data Index: 6208568 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3306. Min Range: -8.3306
Max Act: 7.5181. Min Act: -0.1700
Data Index: 5582294 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3306. Min Range: -8.3306
Max Act: 7.5181. Min Act: -0.1700
Data Index: 8597234 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3306. Min Range: -8.3306
Max Act: 7.5181. Min Act: -0.1700
Data Index: 4793520 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3306. Min Range: -8.3306
Max Act: 7.5181. Min Act: -0.1700
Data Index: 7322810 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3306. Min Range: -8.3306
Max Act: 7.4556. Min Act: -0.1700
Data Index: 5446255 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3306. Min Range: -8.3306
Max Act: 7.4556. Min Act: -0.1700
Data Index: 5421428 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3306. Min Range: -8.3306
Max Act: 7.4243. Min Act: -0.1700
Data Index: 8307556 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3306. Min Range: -8.3306
Max Act: 7.4243. Min Act: -0.1700
Data Index: 5521044 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19