Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4240 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1963. Min Range: -8.1963
Max Act: 8.1963. Min Act: -0.1700
Data Index: 3270986 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1963. Min Range: -8.1963
Max Act: 8.0088. Min Act: -0.1700
Data Index: 3263680 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1963. Min Range: -8.1963
Max Act: 8.0088. Min Act: -0.1700
Data Index: 1394977 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1963. Min Range: -8.1963
Max Act: 8.0088. Min Act: -0.1700
Data Index: 1516615 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1963. Min Range: -8.1963
Max Act: 8.0088. Min Act: -0.1700
Data Index: 5181218 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1963. Min Range: -8.1963
Max Act: 7.9150. Min Act: -0.1700
Data Index: 1423259 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1963. Min Range: -8.1963
Max Act: 7.8525. Min Act: -0.1700
Data Index: 7859262 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1963. Min Range: -8.1963
Max Act: 7.8525. Min Act: -0.1700
Data Index: 3620243 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1963. Min Range: -8.1963
Max Act: 7.8213. Min Act: -0.1700
Data Index: 6550715 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1963. Min Range: -8.1963
Max Act: 7.7900. Min Act: -0.1700
Data Index: 8304405 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1963. Min Range: -8.1963
Max Act: 7.7900. Min Act: -0.1700
Data Index: 3146959 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1963. Min Range: -8.1963
Max Act: 7.7900. Min Act: -0.1700
Data Index: 3481225 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1963. Min Range: -8.1963
Max Act: 7.7588. Min Act: -0.1700
Data Index: 877043 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1963. Min Range: -8.1963
Max Act: 7.7588. Min Act: -0.1700
Data Index: 2496933 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1963. Min Range: -8.1963
Max Act: 7.7275. Min Act: -0.1700
Data Index: 5150483 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1963. Min Range: -8.1963
Max Act: 7.6963. Min Act: -0.1700
Data Index: 8751791 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1963. Min Range: -8.1963
Max Act: 7.7275. Min Act: -0.1700
Data Index: 4632516 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1963. Min Range: -8.1963
Max Act: 7.6650. Min Act: -0.1700
Data Index: 821759 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1963. Min Range: -8.1963
Max Act: 7.6338. Min Act: -0.1700
Data Index: 3681708 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1963. Min Range: -8.1963
Max Act: 7.6338. Min Act: -0.1700
Data Index: 1406759 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19