Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3727 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4923. Min Range: -8.4923
Max Act: 8.4923. Min Act: -0.1700
Data Index: 2264940 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4923. Min Range: -8.4923
Max Act: 8.2423. Min Act: -0.1700
Data Index: 6648668 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4923. Min Range: -8.4923
Max Act: 8.1173. Min Act: -0.1700
Data Index: 2453963 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4923. Min Range: -8.4923
Max Act: 7.8673. Min Act: -0.1700
Data Index: 3857018 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4923. Min Range: -8.4923
Max Act: 7.7423. Min Act: -0.1700
Data Index: 5279976 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4923. Min Range: -8.4923
Max Act: 7.7423. Min Act: -0.1700
Data Index: 4346831 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4923. Min Range: -8.4923
Max Act: 7.6173. Min Act: -0.1700
Data Index: 6086152 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4923. Min Range: -8.4923
Max Act: 7.6173. Min Act: -0.1700
Data Index: 1574450 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4923. Min Range: -8.4923
Max Act: 7.5861. Min Act: -0.1700
Data Index: 2969850 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4923. Min Range: -8.4923
Max Act: 7.4611. Min Act: -0.1700
Data Index: 8270194 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4923. Min Range: -8.4923
Max Act: 7.4611. Min Act: -0.1700
Data Index: 3271905 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4923. Min Range: -8.4923
Max Act: 7.4611. Min Act: -0.1700
Data Index: 7562887 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4923. Min Range: -8.4923
Max Act: 7.4298. Min Act: -0.1700
Data Index: 4040607 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4923. Min Range: -8.4923
Max Act: 7.3673. Min Act: -0.1700
Data Index: 7715193 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4923. Min Range: -8.4923
Max Act: 7.4298. Min Act: -0.1700
Data Index: 5503856 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4923. Min Range: -8.4923
Max Act: 7.3673. Min Act: -0.1700
Data Index: 3598193 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4923. Min Range: -8.4923
Max Act: 7.3673. Min Act: -0.1700
Data Index: 5439058 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4923. Min Range: -8.4923
Max Act: 7.3673. Min Act: -0.1700
Data Index: 7029536 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4923. Min Range: -8.4923
Max Act: 7.3361. Min Act: -0.1700
Data Index: 2969849 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4923. Min Range: -8.4923
Max Act: 7.3361. Min Act: -0.1700
Data Index: 4346829 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19