Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2138 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.6551. Min Act: -0.1700
Data Index: 1761628 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.5926. Min Act: -0.1700
Data Index: 2972347 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.5301. Min Act: -0.1700
Data Index: 5539735 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.4988. Min Act: -0.1700
Data Index: 6772392 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.4988. Min Act: -0.1700
Data Index: 4377698 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.4988. Min Act: -0.1700
Data Index: 5830200 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.5301. Min Act: -0.1700
Data Index: 6782936 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.4675. Min Act: -0.1700
Data Index: 4977787 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.4675. Min Act: -0.1700
Data Index: 5503569 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.4363. Min Act: -0.1700
Data Index: 1629748 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.4675. Min Act: -0.1700
Data Index: 8667877 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.4363. Min Act: -0.1700
Data Index: 7538684 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.4675. Min Act: -0.1700
Data Index: 3375168 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.4675. Min Act: -0.1700
Data Index: 1031856 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.4675. Min Act: -0.1700
Data Index: 2300237 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.4675. Min Act: -0.1700
Data Index: 6239045 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.4675. Min Act: -0.1700
Data Index: 101723 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.4675. Min Act: -0.1700
Data Index: 1814248 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.4363. Min Act: -0.1700
Data Index: 3940370 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6551. Min Range: -4.6551
Max Act: 4.4363. Min Act: -0.1700
Data Index: 4140820 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19