Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2900 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.7111. Min Act: -0.1700
Data Index: 6781207 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.4611. Min Act: -0.1700
Data Index: 5434984 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.4298. Min Act: -0.1700
Data Index: 6204863 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.4298. Min Act: -0.1700
Data Index: 8205659 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.3986. Min Act: -0.1700
Data Index: 4319961 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.4298. Min Act: -0.1700
Data Index: 4356631 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.4298. Min Act: -0.1700
Data Index: 938702 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.4298. Min Act: -0.1700
Data Index: 7710130 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.3986. Min Act: -0.1700
Data Index: 6140526 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.3673. Min Act: -0.1700
Data Index: 1641776 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.3673. Min Act: -0.1700
Data Index: 495951 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.3673. Min Act: -0.1700
Data Index: 3321520 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.3673. Min Act: -0.1700
Data Index: 3040968 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.3673. Min Act: -0.1700
Data Index: 2389504 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.3361. Min Act: -0.1700
Data Index: 854330 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.3048. Min Act: -0.1700
Data Index: 7382881 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.3361. Min Act: -0.1700
Data Index: 8825708 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.3048. Min Act: -0.1700
Data Index: 3200848 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.2736. Min Act: -0.1700
Data Index: 5195090 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7111. Min Range: -6.7111
Max Act: 6.3048. Min Act: -0.1700
Data Index: 1338541 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19