Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 842 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.2378. Min Act: -0.1700
Data Index: 5153895 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.2378. Min Act: -0.1700
Data Index: 1676706 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.2378. Min Act: -0.1700
Data Index: 2651221 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.2378. Min Act: -0.1700
Data Index: 5469007 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.2212. Min Act: -0.1700
Data Index: 2885619 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.2212. Min Act: -0.1700
Data Index: 6360728 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.2047. Min Act: -0.1700
Data Index: 2680924 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.2047. Min Act: -0.1700
Data Index: 6892079 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.2047. Min Act: -0.1700
Data Index: 1589486 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.2047. Min Act: -0.1700
Data Index: 7430869 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.1881. Min Act: -0.1700
Data Index: 4316763 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.2047. Min Act: -0.1700
Data Index: 8567565 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.1881. Min Act: -0.1700
Data Index: 224523 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.1714. Min Act: -0.1700
Data Index: 3131642 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.2047. Min Act: -0.1700
Data Index: 4951648 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.1881. Min Act: -0.1700
Data Index: 1982588 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.1881. Min Act: -0.1700
Data Index: 5434037 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.1714. Min Act: -0.1700
Data Index: 1443519 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.1881. Min Act: -0.1700
Data Index: 725314 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2378. Min Range: -2.2378
Max Act: 2.1714. Min Act: -0.1700
Data Index: 7264807 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19