Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2940 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.8602. Min Act: -0.1700
Data Index: 4350375 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.7977. Min Act: -0.1700
Data Index: 7977649 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.7352. Min Act: -0.1700
Data Index: 5044808 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.7352. Min Act: -0.1700
Data Index: 7904638 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.7352. Min Act: -0.1700
Data Index: 5461895 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.6727. Min Act: -0.1700
Data Index: 3134681 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.6102. Min Act: -0.1700
Data Index: 8118420 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.6727. Min Act: -0.1700
Data Index: 3814145 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.6727. Min Act: -0.1700
Data Index: 6968593 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.6102. Min Act: -0.1700
Data Index: 3323452 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.6102. Min Act: -0.1700
Data Index: 5640459 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.6102. Min Act: -0.1699
Data Index: 7618193 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.6102. Min Act: -0.1700
Data Index: 1048730 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.6102. Min Act: -0.1700
Data Index: 6259304 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.6102. Min Act: -0.1700
Data Index: 8629981 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.6102. Min Act: -0.1700
Data Index: 1622654 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.5477. Min Act: -0.1700
Data Index: 2254018 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.4852. Min Act: -0.1700
Data Index: 5957437 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.5477. Min Act: -0.1700
Data Index: 6707702 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8602. Min Range: -7.8602
Max Act: 7.5477. Min Act: -0.1700
Data Index: 6625270 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19