Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3603 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2438. Min Range: -5.2438
Max Act: 5.2438. Min Act: -0.1700
Data Index: 5741629 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2438. Min Range: -5.2438
Max Act: 4.8375. Min Act: -0.1700
Data Index: 1090491 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2438. Min Range: -5.2438
Max Act: 4.8063. Min Act: -0.1700
Data Index: 1300927 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2438. Min Range: -5.2438
Max Act: 4.8063. Min Act: -0.1700
Data Index: 3996382 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2438. Min Range: -5.2438
Max Act: 4.7750. Min Act: -0.1700
Data Index: 3996384 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2438. Min Range: -5.2438
Max Act: 4.7750. Min Act: -0.1700
Data Index: 2334822 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2438. Min Range: -5.2438
Max Act: 4.7438. Min Act: -0.1700
Data Index: 4635449 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2438. Min Range: -5.2438
Max Act: 4.7125. Min Act: -0.1700
Data Index: 7667853 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2438. Min Range: -5.2438
Max Act: 4.7438. Min Act: -0.1700
Data Index: 4979672 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2438. Min Range: -5.2438
Max Act: 4.6813. Min Act: -0.1700
Data Index: 1902882 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2438. Min Range: -5.2438
Max Act: 4.6188. Min Act: -0.1700
Data Index: 3630572 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2438. Min Range: -5.2438
Max Act: 4.6188. Min Act: -0.1700
Data Index: 3474334 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2438. Min Range: -5.2438
Max Act: 4.5875. Min Act: -0.1700
Data Index: 7339179 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2438. Min Range: -5.2438
Max Act: 4.5875. Min Act: -0.1700
Data Index: 6354148 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2438. Min Range: -5.2438
Max Act: 4.5875. Min Act: -0.1700
Data Index: 4508357 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2438. Min Range: -5.2438
Max Act: 4.5250. Min Act: -0.1700
Data Index: 6020778 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2438. Min Range: -5.2438
Max Act: 4.5250. Min Act: -0.1700
Data Index: 519056 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2438. Min Range: -5.2438
Max Act: 4.5250. Min Act: -0.1700
Data Index: 2342348 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2438. Min Range: -5.2438
Max Act: 4.4938. Min Act: -0.1700
Data Index: 4741996 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2438. Min Range: -5.2438
Max Act: 4.4938. Min Act: -0.1700
Data Index: 935728 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19