Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3052 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0769. Min Range: -3.0769
Max Act: 3.0769. Min Act: -0.1607
Data Index: 493770 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0769. Min Range: -3.0769
Max Act: 3.0769. Min Act: -0.1700
Data Index: 2640838 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0769. Min Range: -3.0769
Max Act: 3.0453. Min Act: -0.1681
Data Index: 2926485 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0769. Min Range: -3.0769
Max Act: 2.9980. Min Act: -0.1700
Data Index: 1091241 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0769. Min Range: -3.0769
Max Act: 2.9980. Min Act: -0.1691
Data Index: 4037280 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0769. Min Range: -3.0769
Max Act: 2.9821. Min Act: -0.1700
Data Index: 2329640 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0769. Min Range: -3.0769
Max Act: 2.9663. Min Act: -0.1693
Data Index: 2386458 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0769. Min Range: -3.0769
Max Act: 2.9505. Min Act: -0.1696
Data Index: 5280557 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0769. Min Range: -3.0769
Max Act: 2.9505. Min Act: -0.1700
Data Index: 3043769 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0769. Min Range: -3.0769
Max Act: 2.9505. Min Act: -0.1698
Data Index: 2015703 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0769. Min Range: -3.0769
Max Act: 2.9347. Min Act: -0.1699
Data Index: 1823272 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0769. Min Range: -3.0769
Max Act: 2.9347. Min Act: -0.1695
Data Index: 7188214 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0769. Min Range: -3.0769
Max Act: 2.9188. Min Act: -0.1696
Data Index: 8658466 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0769. Min Range: -3.0769
Max Act: 2.9347. Min Act: -0.1700
Data Index: 2170667 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0769. Min Range: -3.0769
Max Act: 2.9188. Min Act: -0.1700
Data Index: 8072666 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0769. Min Range: -3.0769
Max Act: 2.9188. Min Act: -0.1700
Data Index: 7228131 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0769. Min Range: -3.0769
Max Act: 2.9030. Min Act: -0.1698
Data Index: 1639845 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0769. Min Range: -3.0769
Max Act: 2.9030. Min Act: -0.1700
Data Index: 2408231 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0769. Min Range: -3.0769
Max Act: 2.9030. Min Act: -0.1700
Data Index: 540900 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0769. Min Range: -3.0769
Max Act: 2.8871. Min Act: -0.1700
Data Index: 6592958 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19