Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6398 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0175. Min Range: -6.0175
Max Act: 6.0175. Min Act: -0.1700
Data Index: 8021433 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.9237. Min Act: -0.1700
Data Index: 5923626 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.9237. Min Act: -0.1700
Data Index: 2661813 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.9237. Min Act: -0.1700
Data Index: 5694666 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.8300. Min Act: -0.1700
Data Index: 5581560 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.8300. Min Act: -0.1700
Data Index: 1294460 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.7987. Min Act: -0.1700
Data Index: 6440517 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.7987. Min Act: -0.1700
Data Index: 1016570 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.7675. Min Act: -0.1700
Data Index: 5328199 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.7675. Min Act: -0.1700
Data Index: 849461 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.7675. Min Act: -0.1700
Data Index: 3871576 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.7362. Min Act: -0.1700
Data Index: 6532385 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.7050. Min Act: -0.1700
Data Index: 8019812 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.7050. Min Act: -0.1700
Data Index: 6337695 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.7050. Min Act: -0.1700
Data Index: 838748 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.7050. Min Act: -0.1700
Data Index: 5346367 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.6737. Min Act: -0.1700
Data Index: 2063249 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.6737. Min Act: -0.1700
Data Index: 6829191 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.6737. Min Act: -0.1700
Data Index: 5863107 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.6737. Min Act: -0.1700
Data Index: 2473932 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19