Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4673 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0384. Min Range: -5.0384
Max Act: 5.0384. Min Act: -0.1700
Data Index: 5690819 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.9447. Min Act: -0.1700
Data Index: 463407 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.9447. Min Act: -0.1700
Data Index: 3303508 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.9134. Min Act: -0.1700
Data Index: 2758081 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.9134. Min Act: -0.1700
Data Index: 7417063 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.8822. Min Act: -0.1700
Data Index: 5317674 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.8822. Min Act: -0.1700
Data Index: 2775010 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.8822. Min Act: -0.1700
Data Index: 3164490 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.8822. Min Act: -0.1700
Data Index: 4397942 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.8509. Min Act: -0.1700
Data Index: 6386126 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.8509. Min Act: -0.1700
Data Index: 6193737 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.8509. Min Act: -0.1700
Data Index: 5605810 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.8197. Min Act: -0.1700
Data Index: 3943682 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.8197. Min Act: -0.1700
Data Index: 8354451 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.7884. Min Act: -0.1700
Data Index: 2612140 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.7884. Min Act: -0.1700
Data Index: 3152686 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.7884. Min Act: -0.1700
Data Index: 5431834 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.7884. Min Act: -0.1700
Data Index: 5438155 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.7884. Min Act: -0.1700
Data Index: 5445643 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0384. Min Range: -5.0384
Max Act: 4.7884. Min Act: -0.1700
Data Index: 4118394 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19