Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2999 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0660. Min Range: -6.0660
Max Act: 6.0660. Min Act: -0.1700
Data Index: 6856747 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0660. Min Range: -6.0660
Max Act: 6.0348. Min Act: -0.1700
Data Index: 472058 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0660. Min Range: -6.0660
Max Act: 5.9410. Min Act: -0.1700
Data Index: 2862663 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0660. Min Range: -6.0660
Max Act: 5.8473. Min Act: -0.1700
Data Index: 7906956 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0660. Min Range: -6.0660
Max Act: 5.8473. Min Act: -0.1700
Data Index: 5556464 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0660. Min Range: -6.0660
Max Act: 5.8160. Min Act: -0.1700
Data Index: 7132704 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0660. Min Range: -6.0660
Max Act: 5.8160. Min Act: -0.1700
Data Index: 2946482 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0660. Min Range: -6.0660
Max Act: 5.7848. Min Act: -0.1700
Data Index: 3219391 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0660. Min Range: -6.0660
Max Act: 5.7223. Min Act: -0.1700
Data Index: 4448029 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0660. Min Range: -6.0660
Max Act: 5.7223. Min Act: -0.1700
Data Index: 1179257 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0660. Min Range: -6.0660
Max Act: 5.7223. Min Act: -0.1700
Data Index: 8022991 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0660. Min Range: -6.0660
Max Act: 5.6598. Min Act: -0.1700
Data Index: 3173473 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0660. Min Range: -6.0660
Max Act: 5.6285. Min Act: -0.1700
Data Index: 3376627 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0660. Min Range: -6.0660
Max Act: 5.6598. Min Act: -0.1700
Data Index: 4878413 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0660. Min Range: -6.0660
Max Act: 5.6285. Min Act: -0.1700
Data Index: 985168 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0660. Min Range: -6.0660
Max Act: 5.6285. Min Act: -0.1700
Data Index: 2513078 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0660. Min Range: -6.0660
Max Act: 5.5973. Min Act: -0.1700
Data Index: 868668 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0660. Min Range: -6.0660
Max Act: 5.5973. Min Act: -0.1700
Data Index: 8199091 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0660. Min Range: -6.0660
Max Act: 5.5660. Min Act: -0.1700
Data Index: 8254649 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0660. Min Range: -6.0660
Max Act: 5.5348. Min Act: -0.1700
Data Index: 3210791 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19