Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2222 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.9917. Min Act: -0.1700
Data Index: 4707381 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.8980. Min Act: -0.1700
Data Index: 3747835 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.8355. Min Act: -0.1700
Data Index: 8043294 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.7730. Min Act: -0.1700
Data Index: 2179280 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.6792. Min Act: -0.1700
Data Index: 2917988 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.6480. Min Act: -0.1700
Data Index: 5688978 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.6480. Min Act: -0.1700
Data Index: 3195403 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.6480. Min Act: -0.1700
Data Index: 401029 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.5542. Min Act: -0.1700
Data Index: 1870778 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.4605. Min Act: -0.1700
Data Index: 8477911 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.4292. Min Act: -0.1700
Data Index: 2921957 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.4292. Min Act: -0.1700
Data Index: 3511921 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.3980. Min Act: -0.1700
Data Index: 682114 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.3980. Min Act: -0.1700
Data Index: 3532406 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.3980. Min Act: -0.1700
Data Index: 4709240 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.3980. Min Act: -0.1700
Data Index: 4647382 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.4292. Min Act: -0.1700
Data Index: 4470955 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.3667. Min Act: -0.1700
Data Index: 7104079 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.3667. Min Act: -0.1700
Data Index: 1259452 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9917. Min Range: -5.9917
Max Act: 5.3355. Min Act: -0.1700
Data Index: 5635178 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19