Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 295 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1886. Min Range: -7.1886
Max Act: 7.1886. Min Act: -0.1700
Data Index: 4467369 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1886. Min Range: -7.1886
Max Act: 6.9698. Min Act: -0.1700
Data Index: 5861340 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1886. Min Range: -7.1886
Max Act: 6.9698. Min Act: -0.1700
Data Index: 6993540 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1886. Min Range: -7.1886
Max Act: 6.9386. Min Act: -0.1700
Data Index: 5943683 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1886. Min Range: -7.1886
Max Act: 6.9073. Min Act: -0.1700
Data Index: 3907072 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1886. Min Range: -7.1886
Max Act: 6.9073. Min Act: -0.1700
Data Index: 2725530 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1886. Min Range: -7.1886
Max Act: 6.8761. Min Act: -0.1700
Data Index: 4926356 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1886. Min Range: -7.1886
Max Act: 6.8136. Min Act: -0.1700
Data Index: 3758304 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1886. Min Range: -7.1886
Max Act: 6.7823. Min Act: -0.1700
Data Index: 2537069 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1886. Min Range: -7.1886
Max Act: 6.7823. Min Act: -0.1700
Data Index: 7571810 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1886. Min Range: -7.1886
Max Act: 6.7511. Min Act: -0.1700
Data Index: 3484388 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1886. Min Range: -7.1886
Max Act: 6.7511. Min Act: -0.1700
Data Index: 4539187 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1886. Min Range: -7.1886
Max Act: 6.7511. Min Act: -0.1700
Data Index: 2703381 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1886. Min Range: -7.1886
Max Act: 6.7511. Min Act: -0.1700
Data Index: 6739781 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1886. Min Range: -7.1886
Max Act: 6.6886. Min Act: -0.1700
Data Index: 7322011 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1886. Min Range: -7.1886
Max Act: 6.6886. Min Act: -0.1700
Data Index: 3590782 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1886. Min Range: -7.1886
Max Act: 6.6573. Min Act: -0.1700
Data Index: 6654373 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1886. Min Range: -7.1886
Max Act: 6.6573. Min Act: -0.1700
Data Index: 1527857 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1886. Min Range: -7.1886
Max Act: 6.6261. Min Act: -0.1700
Data Index: 8139508 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1886. Min Range: -7.1886
Max Act: 6.5948. Min Act: -0.1700
Data Index: 6053950 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19