Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2707 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0505. Min Range: -2.0505
Max Act: 2.0505. Min Act: -0.1700
Data Index: 7057024 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0505. Min Range: -2.0505
Max Act: 1.9999. Min Act: -0.1700
Data Index: 2521426 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0505. Min Range: -2.0505
Max Act: 1.9830. Min Act: -0.1700
Data Index: 5290663 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0505. Min Range: -2.0505
Max Act: 1.9999. Min Act: -0.1700
Data Index: 7474745 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0505. Min Range: -2.0505
Max Act: 1.9660. Min Act: -0.1700
Data Index: 4174503 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0505. Min Range: -2.0505
Max Act: 1.9660. Min Act: -0.1700
Data Index: 8351135 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0505. Min Range: -2.0505
Max Act: 1.9491. Min Act: -0.1700
Data Index: 7296507 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0505. Min Range: -2.0505
Max Act: 1.9491. Min Act: -0.1700
Data Index: 2045791 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0505. Min Range: -2.0505
Max Act: 1.9406. Min Act: -0.1700
Data Index: 270585 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0505. Min Range: -2.0505
Max Act: 1.9151. Min Act: -0.1700
Data Index: 6639115 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0505. Min Range: -2.0505
Max Act: 1.9236. Min Act: -0.1700
Data Index: 3556564 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0505. Min Range: -2.0505
Max Act: 1.9151. Min Act: -0.1700
Data Index: 8197569 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0505. Min Range: -2.0505
Max Act: 1.9066. Min Act: -0.1700
Data Index: 5594707 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0505. Min Range: -2.0505
Max Act: 1.9066. Min Act: -0.1700
Data Index: 6863765 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0505. Min Range: -2.0505
Max Act: 1.8895. Min Act: -0.1700
Data Index: 7306571 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0505. Min Range: -2.0505
Max Act: 1.8810. Min Act: -0.1700
Data Index: 7848265 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0505. Min Range: -2.0505
Max Act: 1.8895. Min Act: -0.1700
Data Index: 8604451 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0505. Min Range: -2.0505
Max Act: 1.8810. Min Act: -0.1700
Data Index: 4691435 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0505. Min Range: -2.0505
Max Act: 1.8724. Min Act: -0.1700
Data Index: 6173106 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0505. Min Range: -2.0505
Max Act: 1.8810. Min Act: -0.1700
Data Index: 2136013 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19