Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5479 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2521. Min Range: -6.2521
Max Act: 6.2521. Min Act: -0.1700
Data Index: 6187427 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2521. Min Range: -6.2521
Max Act: 6.2521. Min Act: -0.1700
Data Index: 3199856 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2521. Min Range: -6.2521
Max Act: 6.0021. Min Act: -0.1700
Data Index: 2134675 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2521. Min Range: -6.2521
Max Act: 5.8458. Min Act: -0.1700
Data Index: 7602526 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2521. Min Range: -6.2521
Max Act: 5.8146. Min Act: -0.1700
Data Index: 4842592 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2521. Min Range: -6.2521
Max Act: 5.7833. Min Act: -0.1700
Data Index: 1700434 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2521. Min Range: -6.2521
Max Act: 5.8146. Min Act: -0.1700
Data Index: 5753536 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2521. Min Range: -6.2521
Max Act: 5.7833. Min Act: -0.1700
Data Index: 172250 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2521. Min Range: -6.2521
Max Act: 5.7833. Min Act: -0.1700
Data Index: 7431225 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2521. Min Range: -6.2521
Max Act: 5.7833. Min Act: -0.1700
Data Index: 7837044 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2521. Min Range: -6.2521
Max Act: 5.7833. Min Act: -0.1700
Data Index: 296925 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2521. Min Range: -6.2521
Max Act: 5.7521. Min Act: -0.1700
Data Index: 3663135 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2521. Min Range: -6.2521
Max Act: 5.7833. Min Act: -0.1700
Data Index: 5395625 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2521. Min Range: -6.2521
Max Act: 5.7833. Min Act: -0.1700
Data Index: 4659738 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2521. Min Range: -6.2521
Max Act: 5.7521. Min Act: -0.1700
Data Index: 6711030 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2521. Min Range: -6.2521
Max Act: 5.7208. Min Act: -0.1700
Data Index: 2863923 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2521. Min Range: -6.2521
Max Act: 5.7521. Min Act: -0.1700
Data Index: 1308357 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2521. Min Range: -6.2521
Max Act: 5.7833. Min Act: -0.1700
Data Index: 1553347 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2521. Min Range: -6.2521
Max Act: 5.7208. Min Act: -0.1700
Data Index: 3791000 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2521. Min Range: -6.2521
Max Act: 5.7208. Min Act: -0.1700
Data Index: 1991179 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19