Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2681 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0352. Min Range: -7.0352
Max Act: 7.0352. Min Act: -0.1700
Data Index: 985375 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0352. Min Range: -7.0352
Max Act: 7.0352. Min Act: -0.1700
Data Index: 1983453 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0352. Min Range: -7.0352
Max Act: 6.8477. Min Act: -0.1700
Data Index: 5122341 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0352. Min Range: -7.0352
Max Act: 6.7852. Min Act: -0.1700
Data Index: 2395031 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0352. Min Range: -7.0352
Max Act: 6.6914. Min Act: -0.1700
Data Index: 5479202 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0352. Min Range: -7.0352
Max Act: 6.6914. Min Act: -0.1700
Data Index: 4357068 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0352. Min Range: -7.0352
Max Act: 6.6602. Min Act: -0.1700
Data Index: 1954728 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0352. Min Range: -7.0352
Max Act: 6.6289. Min Act: -0.1700
Data Index: 6211068 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0352. Min Range: -7.0352
Max Act: 6.5977. Min Act: -0.1700
Data Index: 3693622 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0352. Min Range: -7.0352
Max Act: 6.5977. Min Act: -0.1700
Data Index: 3442706 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0352. Min Range: -7.0352
Max Act: 6.5977. Min Act: -0.1700
Data Index: 1000859 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0352. Min Range: -7.0352
Max Act: 6.5664. Min Act: -0.1700
Data Index: 6211076 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0352. Min Range: -7.0352
Max Act: 6.5664. Min Act: -0.1700
Data Index: 4974357 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0352. Min Range: -7.0352
Max Act: 6.5352. Min Act: -0.1700
Data Index: 6919215 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0352. Min Range: -7.0352
Max Act: 6.5352. Min Act: -0.1700
Data Index: 7465332 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0352. Min Range: -7.0352
Max Act: 6.5352. Min Act: -0.1700
Data Index: 1827319 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0352. Min Range: -7.0352
Max Act: 6.5352. Min Act: -0.1700
Data Index: 6451290 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0352. Min Range: -7.0352
Max Act: 6.5352. Min Act: -0.1700
Data Index: 369978 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0352. Min Range: -7.0352
Max Act: 6.5039. Min Act: -0.1700
Data Index: 387857 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0352. Min Range: -7.0352
Max Act: 6.4727. Min Act: -0.1700
Data Index: 3477645 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19