Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 275 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4160. Min Range: -6.4160
Max Act: 6.4160. Min Act: -0.1700
Data Index: 8180172 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4160. Min Range: -6.4160
Max Act: 6.0410. Min Act: -0.1700
Data Index: 44836 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4160. Min Range: -6.4160
Max Act: 6.1035. Min Act: -0.1700
Data Index: 1842453 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4160. Min Range: -6.4160
Max Act: 6.0410. Min Act: -0.1700
Data Index: 5624032 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4160. Min Range: -6.4160
Max Act: 6.0410. Min Act: -0.1700
Data Index: 5912115 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4160. Min Range: -6.4160
Max Act: 6.0410. Min Act: -0.1700
Data Index: 7962793 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4160. Min Range: -6.4160
Max Act: 5.9785. Min Act: -0.1700
Data Index: 148436 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4160. Min Range: -6.4160
Max Act: 5.9785. Min Act: -0.1700
Data Index: 6386452 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4160. Min Range: -6.4160
Max Act: 5.9160. Min Act: -0.1700
Data Index: 7646841 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4160. Min Range: -6.4160
Max Act: 5.9473. Min Act: -0.1700
Data Index: 2875656 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4160. Min Range: -6.4160
Max Act: 5.9473. Min Act: -0.1700
Data Index: 2004975 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4160. Min Range: -6.4160
Max Act: 5.9160. Min Act: -0.1700
Data Index: 5573500 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4160. Min Range: -6.4160
Max Act: 5.8848. Min Act: -0.1700
Data Index: 342441 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4160. Min Range: -6.4160
Max Act: 5.8848. Min Act: -0.1700
Data Index: 2988484 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4160. Min Range: -6.4160
Max Act: 5.9160. Min Act: -0.1700
Data Index: 7063190 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4160. Min Range: -6.4160
Max Act: 5.9160. Min Act: -0.1700
Data Index: 4002209 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4160. Min Range: -6.4160
Max Act: 5.9160. Min Act: -0.1700
Data Index: 7612814 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4160. Min Range: -6.4160
Max Act: 5.8848. Min Act: -0.1700
Data Index: 1747959 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4160. Min Range: -6.4160
Max Act: 5.9160. Min Act: -0.1700
Data Index: 2853999 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4160. Min Range: -6.4160
Max Act: 5.8535. Min Act: -0.1700
Data Index: 3219540 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19